EL-GY 6123 Image and Video Processing

HomePage.EL-GY6123ImageAndVideoProcessing History

Hide minor edits - Show changes to markup

February 08, 2018, at 09:00 PM EST by Yao Wang -
Changed line 95 from:
to:
February 06, 2018, at 11:02 PM EST by 192.168.131.100 -
Changed line 51 from:

Link(Updated 02/06/2018)

to:

Link (Updated 02/06/2018)

February 06, 2018, at 11:01 PM EST by 192.168.131.100 -
Changed line 53 from:
to:


February 06, 2018, at 11:01 PM EST by 192.168.131.100 -
Changed line 51 from:
 Link (Updated 02/06/2018)
to:

Link(Updated 02/06/2018)

February 06, 2018, at 11:00 PM EST by 192.168.131.100 -
Changed line 51 from:
  Link (Updated 02/06/2018)
to:
 Link (Updated 02/06/2018)
February 06, 2018, at 11:00 PM EST by 192.168.131.100 -
Changed line 51 from:
  Link (Updated 02/06/2018)
to:
  Link (Updated 02/06/2018)
Deleted line 52:
February 06, 2018, at 10:57 PM EST by 192.168.131.100 -
Changed line 51 from:
to:
  Link (Updated 02/06/2018)
February 06, 2018, at 10:55 PM EST by 192.168.131.100 -
Changed line 51 from:
to:
Added line 53:
February 06, 2018, at 10:54 PM EST by 192.168.131.100 -
Changed line 51 from:

Link Δ'(Updated 2/6/2018).

to:
February 06, 2018, at 10:53 PM EST by 192.168.131.100 -
Changed line 51 from:

Link Δ (Updated 2/6/2018).

to:

Link Δ'(Updated 2/6/2018).

February 06, 2018, at 10:35 PM EST by Yao Wang -
February 06, 2018, at 10:32 PM EST by Yao Wang -
February 06, 2018, at 10:30 PM EST by Yao Wang -
Changed line 51 from:

Link (To be updated).

to:

Link Δ (Updated 2/6/2018).

February 06, 2018, at 11:08 AM EST by 172.16.178.71 -
Changed line 28 from:

Amirhossein Khalilian-Gourtani: TBA

to:

Amirhossein Khalilian-Gourtani: Mon: 10:00 am - 11:30 am and Thur: 4:30 pm - 6:30 pm or by appointment

February 05, 2018, at 11:52 AM EST by 172.16.47.146 -
Changed line 27 from:

Chenge Li: Tue. 4:00-5:00 PM and Fri. 1:00-3:00 PM

to:

Chenge Li: Tue. 4:00-5:00 PM and Fri. 3:00-4:00 PM or appointment by email

February 05, 2018, at 11:51 AM EST by 172.16.47.146 -
Changed lines 26-28 from:

TAs: TBA

to:

TAs: Chenge Li: Tue. 4:00-5:00 PM and Fri. 1:00-3:00 PM
Amirhossein Khalilian-Gourtani: TBA

February 02, 2018, at 12:16 PM EST by 172.16.40.19 -
February 01, 2018, at 03:15 PM EST by Yao Wang -
Changed lines 81-83 from:
 Lecture note. Part 2: Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization).  
 Lecture note.
to:
 Lecture note (Updated 1/25/2018). Part 2: Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization).  
 Lecture note (Updated 1/25/2018)
Changed line 88 from:
  • Week 2 (2/2): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators. Lecture note.
to:
  • Week 2 (2/2): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators. Lecture note (Updated 2/1/2018).
February 01, 2018, at 03:04 PM EST by Yao Wang -
Changed line 82 from:
to:
February 01, 2018, at 03:01 PM EST by Yao Wang -
Changed line 82 from:
to:
February 01, 2018, at 02:59 PM EST by Yao Wang -
January 26, 2018, at 12:10 PM EST by 172.16.20.68 -
Changed line 86 from:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5) CA1 Δ
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
January 26, 2018, at 12:09 PM EST by 172.16.20.68 -
Changed line 86 from:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5) CA1 Δ
January 26, 2018, at 12:07 PM EST by 172.16.20.68 -
Changed line 86 from:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
January 26, 2018, at 08:00 AM EST by 172.16.20.68 -
Changed line 17 from:

Chenge Li (MTC2 Room 9.123, cl2840 at nyu dot edu) and Amirhossein Khalilian-Gourtani (MTC2 Room 9.130, akg404 at nyu dot edu)

to:

Chenge Li (MTC2 Room 9.123, cl2840 at nyu dot edu) and Amirhossein Khalilian-Gourtani (MTC2 Room 9.130B, akg404 at nyu dot edu)

January 26, 2018, at 07:56 AM EST by 172.16.20.68 -
Changed lines 82-83 from:
to:
Changed line 86 from:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5) Lecture note.
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
January 26, 2018, at 07:55 AM EST by 172.16.20.68 -
Changed lines 82-83 from:
to:
Changed line 86 from:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5) Lecture note.
January 25, 2018, at 11:19 PM EST by Yao Wang -
Changed lines 97-98 from:
to:
  • Programming assignment 3 (Wavelet-based denoising) (Due 2/22)
Changed lines 103-104 from:
  • Programming assignment 4 (Due 3/8): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features
to:
  • Programming assignment 4 (Due 3/8): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
Changed lines 109-110 from:
to:
  • Programming assignment 5 (Due 3/22): Image Segmentation.
Changed lines 119-120 from:
to:
Changed lines 128-129 from:
to:
  • Programming assignment 7 (Due 5/10): Video Coding
January 25, 2018, at 11:13 PM EST by Yao Wang -
Changed lines 86-87 from:
  • Computer assignment 1 (Due 2/2)
to:
  • Computer assignment 1 (Learning Python and histogram equalization) (Due 2/5)
Added lines 91-92:
  • Computer assignment 2 (2D filtering) (Due 2/8)
Changed lines 97-98 from:
to:
Changed lines 103-104 from:
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features
to:
  • Programming assignment 4 (Due 3/8): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features
Changed lines 109-110 from:
to:
Changed line 118 from:
  • Programming assignment 5 (Due 4/6): Moving object detection.
to:
  • Programming assignment 6 (Due 4/5): Moving object detection.
Changed line 129 from:
to:
January 25, 2018, at 07:29 PM EST by 68.192.154.216 -
Changed line 86 from:
  • Computer assignment 1 (Due 2/2): CA1
to:
  • Computer assignment 1 (Due 2/2)
January 25, 2018, at 07:27 PM EST by 68.192.154.216 -
Added lines 86-87:
  • Computer assignment 1 (Due 2/2): CA1
Deleted line 89:
January 25, 2018, at 07:23 PM EST by 68.192.154.216 -
Changed line 84 from:
to:
  • Tutorial on python (Time /location to be arranged)
January 25, 2018, at 07:21 PM EST by 68.192.154.216 -
Changed line 84 from:
  • Tutorial on python (Time /location to be arranged)
to:
January 21, 2018, at 09:07 PM EST by Yao Wang -
Changed lines 67-68 from:
  • Intro to Python: Basics of Python and Its Application to Image Processing Through OpenCV:Link
to:
  • Basics of Python and Its Application to Image Processing Through OpenCV: Link
January 21, 2018, at 09:05 PM EST by Yao Wang -
Changed lines 67-68 from:
  • Intro to Python: First three slides of the Python course at Columbia:Link
to:
  • Intro to Python: Basics of Python and Its Application to Image Processing Through OpenCV:Link
* Example codes and images used in the above guide: Link
January 21, 2018, at 08:59 PM EST by Yao Wang -
Changed lines 25-26 from:

Yao Wang: Mon. 4-6, and Wed. 4-6PM or appointment by email.
TAs: Thur. 2-5 PM

to:

Yao Wang: Wed. 4- 5:30PM and Fri. 10:30-12:00 or appointment by email.
TAs: TBA

January 21, 2018, at 08:58 PM EST by Yao Wang -
January 02, 2018, at 08:17 AM EST by Yao Wang -
Changed line 49 from:

Link To be updated.

to:

Link (To be updated).

Changed lines 98-99 from:
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features'''
to:
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features
Changed line 146 from:
to:
January 02, 2018, at 08:13 AM EST by 173.63.52.79 -
Changed line 41 from:

Late submission of written assignment and programming assignment will not be accepted unless under extraordinary circumstances and must be approved in advance by the instructor. Students can work in teams, but you must submit you own solutions. For programming assignment, please include your code (with documentation) and results (plots etc.) and discussions.

to:

Written HW will be assigned after each lecture and due at the beginning of the following lecture time. Programming assignment will be due as posted. Late submission of written assignment and programming assignment will not be accepted unless under extraordinary circumstances and must be approved in advance by the instructor. Students can work in teams, but you must submit you own solutions. For programming assignment, please include your code (with documentation) and results (plots etc.) and discussions.

Changed line 49 from:
to:

Link To be updated.

Changed line 98 from:
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).Programming_features
to:
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining). Programming_features'''
January 01, 2018, at 10:27 PM EST by 173.63.52.79 -
Changed lines 86-88 from:
  • Programming assignment 1 (Due 2/9): Linear filtering for noise removal and image sharpening and illustrating the effect in both spatial and frequency

domain. Programming_Filtering

to:
Changed line 96 from:
  • Week 5 (2/23): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC) Lecture note.
to:
  • Week 5 (2/23): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC). Lecture note.
January 01, 2018, at 10:25 PM EST by 173.63.52.79 -
Changed lines 76-77 from:
to:


Changed lines 86-88 from:
  • Programming assignment 1 (Due 2/6): '''Linear filtering for noise removal and image sharpening and illustrating the effect in both spatial and frequency

domain.''' Programming_Filtering

to:
  • Programming assignment 1 (Due 2/9): Linear filtering for noise removal and image sharpening and illustrating the effect in both spatial and frequency

domain. Programming_Filtering

Changed lines 93-106 from:
  • Programming assignment 2 (Due 3/6): Programming _WaveletDenoising
  • Week 5 (2/27): Project Proposal Due
  • Week 5 (2/23): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note
  • Programming assignment 3 (Due 3/20): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).Programming_features
  • Week 6 (3/2): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilizationLecture note
  • Week 7 (3/9): Image segmentation: region growing, split and merge, Otsu’s method, K-means, GMM clustering. ''Lecture note.
  • Programming assignment 4 (Due 3/27): Image Segmentation. Programming_Kmeans
to:
  • Programming assignment 2 (Due 3/2): Programming _WaveletDenoising
  • Week 5 (2/23): Project Proposal Due
  • Week 5 (2/23): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC) Lecture note.
  • Programming assignment 3 (Due 3/9): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).Programming_features
  • Week 6 (3/2): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilization. Lecture note
  • Week 7 (3/9): Image segmentation: region growing, split and merge, Otsu’s method, K-means, GMM clustering. Lecture note.
  • Programming assignment 4 (Due 3/23): Image Segmentation. Programming_Kmeans
Changed lines 114-115 from:
to:
Changed line 125 from:
to:
January 01, 2018, at 10:13 PM EST by 173.63.52.79 -
Deleted line 55:


Deleted line 73:
Changed lines 86-87 from:
to:
Added line 95:
Added line 97:
Added line 122:
January 01, 2018, at 10:10 PM EST by 173.63.52.79 -
Changed lines 57-58 from:

Links to Resources (lecture notes and sample exams) in Previous Offerings:

to:

Links to Resources (lecture notes and sample exams) in Previous Offerings:

Changed lines 62-64 from:
  • The coursera image processing course by Prof. Katsaggelos:Link
  • The image processing course at Stanford:Link
  • The computer vision course at U. Washington:Link
to:
  • The coursera image processing course by Prof. Katsaggelos: Link
  • The image processing course at Stanford: Link
  • The computer vision course at U. Washington: Link
January 01, 2018, at 10:08 PM EST by 173.63.52.79 -
Changed line 47 from:


to:
Changed line 51 from:


to:
Deleted line 64:
Changed line 68 from:
  1. Intro to Python: First three slides of the Python course at Columbia:Link
to:
  • Intro to Python: First three slides of the Python course at Columbia:Link
January 01, 2018, at 10:05 PM EST by 173.63.52.79 -
Changed line 44 from:

Project Guideline:

to:

Project Guideline:

Changed line 48 from:

Suggested Project List:

to:

Suggested Project List:

January 01, 2018, at 10:04 PM EST by 173.63.52.79 -
Changed lines 25-26 from:

Mon. 4-6, and Wed. 4-6PM or appointment by email.
Thur. 2-5 PM (TA's office hours)

to:

Yao Wang: Mon. 4-6, and Wed. 4-6PM or appointment by email.
TAs: Thur. 2-5 PM

Changed line 41 from:

Late submission of written assignment and programming assignment will not be accepted unless under special circumstances and must be approved in advance by the instructor. Students can work in teams, but you must submit you own solutions. For programming assignment, please include your code (with documentation) and results (plots etc.) and discussions.

to:

Late submission of written assignment and programming assignment will not be accepted unless under extraordinary circumstances and must be approved in advance by the instructor. Students can work in teams, but you must submit you own solutions. For programming assignment, please include your code (with documentation) and results (plots etc.) and discussions.

Changed lines 43-46 from:

Project Guideline
Project List
Sample Images
Middelbury Stereo Image Database

to:


Project Guideline:
Link


Suggested Project List:
Link


Sample Data:
Sample Images
Middelbury Stereo Image Database

January 01, 2018, at 09:57 PM EST by 173.63.52.79 -
Changed lines 13-14 from:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.

 Homepage
to:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu. Homepage

January 01, 2018, at 09:56 PM EST by 173.63.52.79 -
Changed lines 13-14 from:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.Homepage

to:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.

 Homepage
Changed line 18 from:

Yilin Song (MTC2 Room 9.123, ys1297 at nyu dot edu) and Anti-Chiang (MTC2 Room 9.123, atc327 at nyu dot edu)

to:

Chenge Li (MTC2 Room 9.123, cl2840 at nyu dot edu) and Amirhossein Khalilian-Gourtani (MTC2 Room 9.130, akg404 at nyu dot edu)

Changed line 22 from:

Monday 12:25 AM-2:55PM, Room RH215.

to:

Friday 12:25 AM-2:55PM, Room RH215.

Changed line 26 from:

Wed. 4-6PM and Thur 4-6 PM or appointment by email.

to:

Mon. 4-6, and Wed. 4-6PM or appointment by email.

Changed line 38 from:

Exam: 40%, Final Project: 30%, Programming assignments: 30%, Written homework will be assigned but not graded. Solution to written HW will be provided.

to:

Exam: 40%, Final Project: 30%, Programming assignments: 20%, Written assignments: 10%.

Changed line 42 from:

Late submissions of programming assignment will be accepted up to 7 days after the deadline, with penalty of 1 pt for each day (Each assignment has 10pt). Students can work in teams (at most 3 people) and each team should submit one completed assignment. You should include your code (with documentation) and results (plots etc.) and discussions. When working in teams, each person must understand what others did and what are included in the assignment!

to:

Late submission of written assignment and programming assignment will not be accepted unless under special circumstances and must be approved in advance by the instructor. Students can work in teams, but you must submit you own solutions. For programming assignment, please include your code (with documentation) and results (plots etc.) and discussions.

Changed lines 72-75 from:
to:
  • Week 1 (1/26): Part 1: Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Lecture note. Part 2: Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization). Lecture note.
Changed lines 77-80 from:
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.Lecture note on Fourier Transform and linear filtering
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering
  • Week 3 (2/6): Image sampling and resizing. Design of interpolation filters. Multiresolution representation: Pyramid and wavelets.Lecture note on ImageSampling , Lecture note on Wavelet Δ
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).
to:
  • Week 2 (2/2): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators. Lecture note.
  • Programming assignment 1 (Due 2/6): '''Linear filtering for noise removal and image sharpening and illustrating the effect in both spatial and frequency

domain.'' 'Programming_Filtering

  • Week 3 (2/9): Image sampling and resizing. Design of interpolation filters. Multiresolution representation: Pyramid and wavelets. Lecture note on ImageSampling, Lecture note on Wavelet. Δ
  • Week 4 (TBA): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).
Changed line 88 from:
  • 2/20/17 Presidents’ Day. No class.
to:
Changed line 90 from:
  • Week 5 (2/27): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note on Feature
to:
  • Week 5 (2/23): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note
Changed lines 92-98 from:
  • Week 6 (3/6): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilizationLecture note on geometric transformation
  • 3/13/17-3/19/17: Spring Recess
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Lecture note on image segmentation
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans
  • Week 8 (3/27): Midterm Project Feedback (Individual meeting)
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)Lecture note on MotionEstimation
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.Lecture note on Moving object detection
to:
  • Week 6 (3/2): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilizationLecture note
  • Week 7 (3/9): Image segmentation: region growing, split and merge, Otsu’s method, K-means, GMM clustering. ''Lecture note.
  • Programming assignment 4 (Due 3/27): Image Segmentation. Programming_Kmeans
  • 3/12/17-3/16/17: Spring Recess
  • Week 8 (3/23): Midterm Project Feedback (Individual meeting)
  • Week 8 (3/23): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications). Lecture note.
  • Week 9 (3/30): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation. Lecture note.
Changed lines 107-110 from:
  • Week 10 (4/10): Stereo and multiview video: depth from disparity, disparity estimation, view synthesis. Depth camera (Kinect). 360 video camera and view stitching. Light field imaging.Lecture note on Stereo and Multiview Video Processing
  • Week 11 (4/17): Exam
  • Week 12 (4/24): Fundamentals of source coding: characterization of random sources by entropy, binary encoding, scalar quantization, vector quantization. Lecture note on source coding basics.
  • Week 13 (5/1): Transform coding: Image representation using unitary transforms (orthogonal bases), Transform coding, JPEG image compression standard, Image representation using wavelet transform; concept of layered coding, JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding.
to:
  • Week 10 (4/6): Stereo and multiview video: depth from disparity, disparity estimation, view synthesis. Depth camera (Kinect). 360 video camera and view stitching. Light field imaging. Lecture note.
  • Week 11 (4/13): Exam
  • Week 12 (4/20): Fundamentals of source coding: characterization of random sources by entropy, binary encoding, scalar quantization, vector quantization. Lecture note.
  • Week 13 (4/27): Transform coding: Image representation using unitary transforms (orthogonal bases), Transform coding, JPEG image compression standard, Image representation using wavelet transform; concept of layered coding, JPEG2000 image compression standard. Lecture note.
Changed lines 116-118 from:
  • Week 14 (5/8): Part 1: Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note on Video Coding. Part 2: Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. Error resilience issues. Adaptive Video Streaming (DASH). Lecture note on Video Coding Standards.
  • Week 15 (5/15): Project Presentation.
  • 5/17: Project Report and all other material must be uploaded.
to:
  • Week 14 (5/4): Part 1: Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note. Part 2: Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. Error resilience issues. Adaptive Video Streaming (DASH). Lecture note.
  • Week 15 (5/11): Project Presentation.
  • 5/18: Project Report and all other material must be uploaded.
May 14, 2017, at 12:01 AM EST by 108.35.153.58 -
Changed lines 92-95 from:
  • Week 12 (4/24): Fundamentals of source coding: characterization of random sources by entropy. binary encoding, scalar quantization, vector quantization. Lecture note on source coding basics.
  • Week 13 (5/1): Transform coding: Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding
  • Programming assignment 6 (Due 5/8): Video coding. Video Coding
  • Week 14 (5/8): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note on Block-Based Hybrid Video Coding Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH). ''', Lecture note on Video Coding Standards
to:
  • Week 12 (4/24): Fundamentals of source coding: characterization of random sources by entropy, binary encoding, scalar quantization, vector quantization. Lecture note on source coding basics.
  • Week 13 (5/1): Transform coding: Image representation using unitary transforms (orthogonal bases), Transform coding, JPEG image compression standard, Image representation using wavelet transform; concept of layered coding, JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding.
  • Programming assignment 6 (Due 5/17): Video coding. Video Coding Assignment
  • Week 14 (5/8): Part 1: Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note on Video Coding. Part 2: Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. Error resilience issues. Adaptive Video Streaming (DASH). Lecture note on Video Coding Standards.
May 13, 2017, at 11:55 PM EST by 108.35.153.58 -
Changed lines 92-93 from:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding
  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity.Lecture note on Video coding
to:
  • Week 12 (4/24): Fundamentals of source coding: characterization of random sources by entropy. binary encoding, scalar quantization, vector quantization. Lecture note on source coding basics.
  • Week 13 (5/1): Transform coding: Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding
Changed line 95 from:
to:
  • Week 14 (5/8): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note on Block-Based Hybrid Video Coding Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH). ''', Lecture note on Video Coding Standards
Changed line 97 from:
  • 5/20: Project Report and all other material must be uploaded.
to:
  • 5/17: Project Report and all other material must be uploaded.
May 07, 2017, at 04:00 PM EST by 192.168.130.136 -
Deleted line 94:
May 07, 2017, at 03:59 PM EST by 192.168.130.136 -
Changed lines 94-95 from:
  • Programming assignment 6 (Due 5/8): Video coding.
to:
  • Programming assignment 6 (Due 5/8): Video coding. Video Coding
May 07, 2017, at 03:57 PM EST by 192.168.130.136 -
Changed line 92 from:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. , Lecture note on unitary transforms and Transform Coding
to:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note on unitary transforms and Transform Coding
May 07, 2017, at 03:56 PM EST by 192.168.130.136 -
Changed line 92 from:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Lecture note(updated 4/10/2016Week 11 ( Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note(updated 4/25/2016)
to:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. , Lecture note on unitary transforms and Transform Coding
Changed line 95 from:
to:
May 07, 2017, at 03:54 PM EST by 192.168.130.136 -
Changed lines 95-98 from:
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH)

Lecture note on Block-Based Hybrid Video Coding Lecture note on Video Coding Standards Lecture note on Transform Coding

to:
May 07, 2017, at 03:53 PM EST by 192.168.130.136 -
Changed line 93 from:
  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity.Lecture note(updated 4/25/2016)
to:
  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity.Lecture note on Video coding
Changed lines 95-98 from:
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH) Lecture note(updated 5/7/2016)
to:
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH)

Lecture note on Block-Based Hybrid Video Coding Lecture note on Video Coding Standards Lecture note on Transform Coding

April 10, 2017, at 10:31 AM EST by 172.16.43.43 -
Changed line 90 from:
  • Week 10 (4/10): Stereo and multiview video: depth from disparity, disparity estimation, view synthesis. Depth camera (Kinect). 360 video camera and view stitching. Light field imaging.
to:
April 08, 2017, at 08:51 PM EST by 68.175.99.86 -
Changed lines 107-109 from:
  • S15 Final Exam solution
  • S16_midterm solution
  • S16 final exam solution
to:
  • S15 Final Exam solution
  • S16_midterm solution
  • S16 final exam solution
April 08, 2017, at 08:49 PM EST by 68.175.99.86 -
Changed line 106 from:
  • S15_midterm_w_solution
to:
  • S15_midterm_w_solution
April 08, 2017, at 08:47 PM EST by 68.175.99.86 -
Changed line 106 from:
  • S15_midterm_w_solution
to:
  • S15_midterm_w_solution
April 06, 2017, at 12:59 PM EST by 172.16.45.72 -
Changed line 82 from:
to:
Changed lines 84-85 from:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Lecture note on image segmentation'''
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans'''
to:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Lecture note on image segmentation
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans
Changed lines 87-89 from:
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)Lecture note on MotionEstimation'''
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.Lecture note on Moving object detection'''
  • Programming assignment 5 (Due 4/10): Moving object detection Programming_Moving object detection'''
to:
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)Lecture note on MotionEstimation
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.Lecture note on Moving object detection
  • Programming assignment 5 (Due 4/10): Moving object detection Programming_Moving object detection
April 06, 2017, at 12:57 PM EST by 172.16.45.72 -
Changed line 85 from:
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans
to:
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans'''
April 06, 2017, at 12:57 PM EST by 172.16.45.72 -
Changed line 82 from:
  • Week 6 (3/6): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilization
to:
Changed lines 84-85 from:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.
to:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Lecture note on image segmentation'''
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.Programming_Kmeans
Changed lines 87-89 from:
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.
  • Programming assignment 5 (Due 4/10): Moving object detection
to:
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)Lecture note on MotionEstimation'''
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.Lecture note on Moving object detection'''
  • Programming assignment 5 (Due 4/10): Moving object detection Programming_Moving object detection'''
March 02, 2017, at 11:30 PM EST by 192.168.130.18 -
Changed line 81 from:
  • Programming assignment 3 (Due 3/20): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
to:
  • Programming assignment 3 (Due 3/20): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).Programming_features
Changed line 84 from:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Programming_features
to:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
March 02, 2017, at 11:29 PM EST by 192.168.130.18 -
Changed line 84 from:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
to:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).Programming_features
March 02, 2017, at 11:19 PM EST by 68.175.99.86 -
Changed line 77 from:
to:
Changed line 81 from:
  • Programming assignment 3 (Due 3/6): Implement a specified segmentation method yourself. Compare different methods using available implementations.
to:
  • Programming assignment 3 (Due 3/20): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
Changed line 85 from:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
to:
  • Programming assignment 4 (Due 3/27): Implement a specified segmentation method yourself. Compare different methods using available implementations.
March 02, 2017, at 04:17 PM EST by 172.16.47.130 -
Changed line 76 from:
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).Lecture note on Sparse Representation
to:
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).
March 02, 2017, at 03:20 PM EST by 172.16.46.93 -
Changed line 80 from:
  • Week 5 (2/27): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
to:
  • Week 5 (2/27): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note on Feature
Changed line 82 from:
  • Week 6 (3/6): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note on Feature
to:
  • Week 6 (3/6): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilization
Changed line 84 from:
  • Week 7 (3/20): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilization
to:
  • Week 7 (3/20): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
March 02, 2017, at 01:13 PM EST by 172.16.47.130 -
Deleted line 113:


March 02, 2017, at 01:13 PM EST by 172.16.47.130 -
Added line 112:
Added line 115:


Added line 117:
March 02, 2017, at 01:11 PM EST by 172.16.47.130 -
Changed line 112 from:
to:
March 02, 2017, at 01:11 PM EST by 172.16.47.130 -
Changed line 112 from:
to:
March 02, 2017, at 01:10 PM EST by 172.16.47.130 -
Changed line 85 from:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).sample image
to:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
Added lines 110-112:


Sample Images:
sample image

March 01, 2017, at 05:27 PM EST by 172.16.47.130 -
Changed line 85 from:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).sample image'''
to:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).sample image
March 01, 2017, at 05:26 PM EST by 172.16.47.130 -
Changed line 82 from:
  • Week 6 (3/6): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)
to:
  • Week 6 (3/6): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)Lecture note on Feature
Changed line 85 from:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
to:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).sample image'''
February 24, 2017, at 10:53 AM EST by 172.16.248.201 -
February 17, 2017, at 09:42 PM EST by 192.168.128.225 -
February 17, 2017, at 09:41 PM EST by 192.168.128.225 -
Changed line 74 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering.pdf
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering
February 17, 2017, at 09:41 PM EST by 192.168.128.225 -
Changed lines 76-77 from:
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).
  • Programming assignment 2 (Due 2/27): '''Programming _WaveletDenoising
to:
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).Lecture note on Sparse Representation
  • Programming assignment 2 (Due 2/27): Programming _WaveletDenoising
February 17, 2017, at 09:33 PM EST by 192.168.128.225 -
Changed line 77 from:
to:
February 17, 2017, at 09:33 PM EST by 192.168.128.225 -
Changed line 77 from:
  • Programming assignment 2 (Due 2/27): Wavelet based image denoising
to:
February 06, 2017, at 12:55 PM EST by 172.17.107.170 -
Changed line 25 from:

Wed. 4-6PM and Thur 4-6 PM or appointment by email.

to:

Wed. 4-6PM and Thur 4-6 PM or appointment by email.

February 06, 2017, at 12:54 PM EST by 172.17.107.170 -
Added line 26:

Thur. 2-5 PM (TA's office hours)

February 05, 2017, at 05:01 PM EST by 192.168.130.233 -
Changed line 74 from:
  • Week 3 (2/6): Image sampling and resizing. Design of interpolation filters. Multiresolution representation: Pyramid and wavelets.
to:
February 04, 2017, at 09:21 PM EST by 142.255.110.97 -
Changed line 73 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering.pdf
February 04, 2017, at 09:21 PM EST by 142.255.110.97 -
Changed line 73 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming assignment 1
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming_Filtering
February 03, 2017, at 01:53 PM EST by 172.17.107.170 -
February 01, 2017, at 04:03 PM EST by 172.17.106.154 -
Changed line 70 from:
to:
January 30, 2017, at 11:37 PM EST by 192.168.128.176 -
Changed line 70 from:
to:
January 30, 2017, at 10:08 PM EST by 192.168.128.176 -
Changed line 70 from:
to:
January 30, 2017, at 10:07 PM EST by 192.168.128.176 -
Changed lines 70-71 from:

Solution of Written Homework 1

to:
January 30, 2017, at 10:06 PM EST by 192.168.128.176 -
Changed line 71 from:
to:
January 30, 2017, at 10:05 PM EST by 192.168.128.176 -
Changed line 70 from:
to:
January 30, 2017, at 10:04 PM EST by 192.168.128.176 -
Added line 71:
January 29, 2017, at 01:08 AM EST by 192.168.128.16 -
Changed line 73 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.'Programming assignment 1
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.Programming assignment 1
January 29, 2017, at 01:07 AM EST by 192.168.128.16 -
Changed line 73 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.'Programming assignment 1
January 29, 2017, at 12:34 AM EST by 192.168.130.80 -
Changed line 72 from:
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.Lecture note on Fourier Transform ans linear filtering
to:
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.Lecture note on Fourier Transform and linear filtering
January 29, 2017, at 12:32 AM EST by 192.168.130.80 -
Changed line 72 from:
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.
to:
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.Lecture note on Fourier Transform ans linear filtering
January 27, 2017, at 05:53 PM EST by 172.17.106.60 -
Changed line 44 from:

Sample Images

to:

Sample Images

January 27, 2017, at 05:52 PM EST by 172.17.106.60 -
Changed lines 42-43 from:

Project Guideline

to:

Project Guideline
Project List

January 24, 2017, at 01:21 PM EST by 172.17.109.27 -
Deleted lines 45-48:

Project Topics:
Link

January 24, 2017, at 12:04 PM EST by 172.17.109.27 -
Changed line 47 from:

to:

Link

January 24, 2017, at 12:04 PM EST by 172.17.109.27 -
Changed line 47 from:

Link

to:

January 24, 2017, at 11:27 AM EST by 172.17.109.27 -
Changed line 46 from:

Project Topic:

to:

Project Topics:

January 24, 2017, at 11:26 AM EST by 172.17.109.27 -
Added lines 46-48:

Project Topic:
Link

January 21, 2017, at 03:03 PM EST by 142.255.110.97 -
Changed line 70 from:
to:
January 21, 2017, at 03:02 PM EST by 142.255.110.97 -
Changed line 70 from:
to:
January 21, 2017, at 03:01 PM EST by 142.255.110.97 -
Changed line 70 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization): file 1 , file2
to:
January 21, 2017, at 02:46 PM EST by 142.255.110.97 -
Deleted line 70:
January 21, 2017, at 02:46 PM EST by 142.255.110.97 -
Changed line 70 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization) : file 1 , file2
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization): file 1 , file2
January 21, 2017, at 02:45 PM EST by 142.255.110.97 -
Changed line 70 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 , file2
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization) : file 1 , file2
January 21, 2017, at 02:44 PM EST by 142.255.110.97 -
Changed line 70 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 file2
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 , file2
January 21, 2017, at 02:43 PM EST by 142.255.110.97 -
Changed lines 70-71 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 file2
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 file2
January 21, 2017, at 02:38 PM EST by 142.255.110.97 -
Changed lines 70-71 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)ImageFormationContrastEnhancement
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)file 1 file2
January 21, 2017, at 02:37 PM EST by 142.255.110.97 -
Changed lines 70-71 from:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)
to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)ImageFormationContrastEnhancement
January 21, 2017, at 12:11 PM EST by 142.255.110.97 -
Added lines 64-65:
  • Codeacdemy : python
  • Anaconda
January 19, 2017, at 02:31 PM EST by 172.17.109.27 -
January 19, 2017, at 12:18 PM EST by 172.17.109.27 -
Changed line 74 from:
  • Programming assignment 2 (Due 2/27): Wavelet based image denoising
to:
  • Programming assignment 2 (Due 2/27): Wavelet based image denoising
Changed line 78 from:
  • Programming assignment 3 (Due 3/6): Implement a specified segmentation method yourself. Compare different methods using available implementations.
to:
  • Programming assignment 3 (Due 3/6): Implement a specified segmentation method yourself. Compare different methods using available implementations.
Changed line 82 from:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
to:
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
Changed line 86 from:
  • Programming assignment 5 (Due 4/10): Moving object detection
to:
  • Programming assignment 5 (Due 4/10): Moving object detection
Changed line 91 from:
  • Programming assignment 6 (Due 5/8): Video coding.
to:
  • Programming assignment 6 (Due 5/8): Video coding.
January 19, 2017, at 12:17 PM EST by 172.17.109.27 -
Changed line 71 from:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
to:
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
January 19, 2017, at 11:59 AM EST by 172.17.109.27 -
January 18, 2017, at 10:01 PM EST by 142.255.110.97 -
Changed lines 47-48 from:

Links to resources (lecture notes and sample exams) in previous offerings:

to:

Links to Resources (lecture notes and sample exams) in Previous Offerings:

Changed line 101 from:

Sample exams:

to:

Sample Exams:

January 18, 2017, at 09:43 PM EST by 142.255.110.97 -
January 18, 2017, at 09:43 PM EST by 142.255.110.97 -
Changed line 17 from:

Yilin Song (MTC2 Room 9.123, ys1297 at nyu dot edu) and Anti-Chiang (MTC2 Room 9.123, dawnandyknight at nyu dot edu)

to:

Yilin Song (MTC2 Room 9.123, ys1297 at nyu dot edu) and Anti-Chiang (MTC2 Room 9.123, atc327 at nyu dot edu)

January 18, 2017, at 05:20 PM EST by 142.255.110.97 -
January 18, 2017, at 05:20 PM EST by 142.255.110.97 -
Changed line 13 from:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.Homepage

to:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.Homepage

January 18, 2017, at 05:19 PM EST by 142.255.110.97 -
Changed line 5 from:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
to:

This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

Added line 9:

Graduate status. EL-GY 6113 and EL-GY 6303 preferred but not required. Undergraduate students must have completed EE-UY 3054 Signals and systems and EE-UY 2233 Probability.

Deleted line 10:

Graduate status. EL-GY 6113 and EL-GY 6303 preferred but not required. Undergraduate students must have completed EE-UY 3054 Signals and systems and EE-UY 2233 Probability.

Deleted line 11:


Added line 13:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu.Homepage

Deleted line 14:

Professor Yao Wang, MTC2 Room 9.122, (646)-997-3469, Email: yaowang at nyu dot edu. Homepage: http://eeweb.poly.edu/~yao

Deleted line 15:


Added line 17:

Yilin Song (MTC2 Room 9.123, ys1297 at nyu dot edu) and Anti-Chiang (MTC2 Room 9.123, dawnandyknight at nyu dot edu)

Deleted line 18:

Yilin Song (MTC2 Room 9.123, ys1297 at nyu dot edu) and Anti-Chiang (MTC2 Room 9.123, dawnandyknight at nyu dot edu)

Deleted line 19:


Added line 21:

Monday 12:25 AM-2:55PM, Room RH215.

Deleted line 22:

Monday 12:25 AM-2:55PM, Room RH215.

Deleted line 23:


Added line 25:

Wed. 4-6PM and Thur 4-6 PM or appointment by email.

Deleted line 26:

Wed. 4-6PM and Thur 4-6 PM or appointment by email.

Deleted line 27:


Added line 36:

Exam: 40%, Final Project: 30%, Programming assignments: 30%, Written homework will be assigned but not graded. Solution to written HW will be provided.

Deleted line 37:

Exam: 40%, Final Project: 30%, Programming assignments: 30%, Written homework will be assigned but not graded. Solution to written HW will be provided.

Deleted line 38:


Added line 40:

Late submissions of programming assignment will be accepted up to 7 days after the deadline, with penalty of 1 pt for each day (Each assignment has 10pt). Students can work in teams (at most 3 people) and each team should submit one completed assignment. You should include your code (with documentation) and results (plots etc.) and discussions. When working in teams, each person must understand what others did and what are included in the assignment!

Deleted lines 41-42:

Late submissions of programming assignment will be accepted up to 7 days after the deadline, with penalty of 1 pt for each day (Each assignment has 10pt). Students can work in teams (at most 3 people) and each team should submit one completed assignment. You should include your code (with documentation) and results (plots etc.) and discussions. When working in teams, each person must understand what others did and what are included in the assignment!

Deleted line 108:


January 18, 2017, at 05:16 PM EST by 142.255.110.97 -
Changed line 5 from:

:This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

to:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
January 18, 2017, at 05:15 PM EST by 142.255.110.97 -
Changed line 5 from:
  1. This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
to:

:This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

January 18, 2017, at 05:14 PM EST by 142.255.110.97 -
Changed line 5 from:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
to:
  1. This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
January 18, 2017, at 05:14 PM EST by 142.255.110.97 -
Changed line 5 from:

_>This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

to:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
January 18, 2017, at 05:14 PM EST by 142.255.110.97 -
Changed line 5 from:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
to:

_>This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

January 18, 2017, at 05:12 PM EST by 142.255.110.97 -
Deleted line 4:


January 18, 2017, at 05:11 PM EST by 142.255.110.97 -
Changed line 6 from:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
to:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
January 18, 2017, at 05:10 PM EST by 142.255.110.97 -
Changed line 6 from:

This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.

to:
This course introduces fundamentals of image and video processing, including color image capture and representation; contrast enhancement; spatial domain filtering; two-dimensional (2D) Fourier transform and frequency domain interpretation of linear convolution; image sampling and resizing; multi-resolution image representation using pyramid and wavelet transforms; feature point detection and global alignment between images based on feature correspondence; geometric transformation, image registration; video motion characterization and estimation; video stabilization and panoramic view generation; image and video segmentation; selected advanced image processing techniques; basic compression techniques and standards (JPEG image compression standard; wavelet transform and JPEG2000 standard; video compression using adaptive spatial and temporal prediction; video coding standards (MPEGx/H26x); Stereo and multi- view image and video processing (depth from disparity, disparity estimation, video synthesis, compression). Students will learn to implement selected algorithms in Python. A term project will be required.
January 18, 2017, at 05:08 PM EST by 142.255.110.97 -
Changed lines 112-114 from:
  • S15 Final Exam solution
  • S16_midterm solution
  • S16 final exam solution
to:
  • S15 Final Exam solution
  • S16_midterm solution
  • S16 final exam solution
January 18, 2017, at 05:07 PM EST by 142.255.110.97 -
Changed lines 57-63 from:
  1. EL 5123 Image Processing
  2. EL 6123 Video Processing
  3. EL 6123 Image and Video Processing (S16)
  4. The coursera image processing course by Prof. Katsaggelos:Link
  5. The image processing course at Stanford:Link
  6. The computer vision course at U. Washington:Link
to:
  • EL 5123 Image Processing
  • EL 6123 Video Processing
  • EL 6123 Image and Video Processing (S16)
  • The coursera image processing course by Prof. Katsaggelos:Link
  • The image processing course at Stanford:Link
  • The computer vision course at U. Washington:Link
Changed lines 68-71 from:
  1. OpenCV: an open source package including many computer vision algorithms
  2. Numpy
  3. Scipy
  4. Matrix Reference Manual
to:
  • OpenCV: an open source package including many computer vision algorithms
  • Numpy
  • Scipy
  • Matrix Reference Manual
Changed lines 111-114 from:
  1. S15_midterm_w_solution
  2. S15 Final Exam solution
  3. S16_midterm solution
  4. S16 final exam solution
to:
  • S15_midterm_w_solution
  • S15 Final Exam solution
  • S16_midterm solution
  • S16 final exam solution
January 18, 2017, at 05:06 PM EST by 142.255.110.97 -
Changed lines 50-52 from:

Project Guideline
Sample Images
'''Middelbury Stereo Image Database

to:

Project Guideline
Sample Images
Middelbury Stereo Image Database

January 18, 2017, at 05:05 PM EST by 142.255.110.97 -
Changed lines 97-103 from:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Lecture note
    (updated 4/10/2016Week 11 ( Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note

(updated 4/25/2016)

  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note

(updated 4/25/2016)

to:
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Lecture note(updated 4/10/2016Week 11 ( Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note(updated 4/25/2016)
  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity.Lecture note(updated 4/25/2016)
Changed lines 100-101 from:
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH) Lecture note

(updated 5/7/2016)

to:
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH) Lecture note(updated 5/7/2016)
January 18, 2017, at 05:05 PM EST by 142.255.110.97 -
Changed lines 80-95 from:
to:
  • Week 3 (2/6): Image sampling and resizing. Design of interpolation filters. Multiresolution representation: Pyramid and wavelets.
  • Week 4 (2/13): Sparsity and dictionary based image processing: Image representation using orthonormal transform/dictionary. Sparsity assumption. General formulation of image enhancement as an optimization problem, L0 vs. L1 vs. L2 prior, Basic optimization techniques. Applications in debluring, denoising, inpainting, compressive sensing, superresolution, dictionary learning (PCA and KSVD).
  • Programming assignment 2 (Due 2/27): Wavelet based image denoising
  • 2/20/17 Presidents’ Day. No class.
  • Week 5 (2/27): Project Proposal Due
  • Week 5 (2/27): Image segmentation: region growing, split and merge, Otsu’s method, K-means, mean-shift, normalized cut, graph cut (optional).
  • Programming assignment 3 (Due 3/6): Implement a specified segmentation method yourself. Compare different methods using available implementations.
  • Week 6 (3/6): Feature detection (SIFT), feature descriptors and matching, and feature based global mapping estimation (Robust least squares and RANSAC)
  • 3/13/17-3/19/17: Spring Recess
  • Week 7 (3/20): Geometric transformation. Image warping. Image morphing. Panoramic view stitching. Video stabilization
  • Programming assignment 4 (Due 3/27): Stitching a panoramic picture (Feature detection, finding global mapping, warping, combining).
  • Week 8 (3/27): Midterm Project Feedback (Individual meeting)
  • Week 8 (3/27): Dense motion/displacement estimation: optical flow equation, optical flow estimation; block matching, multi-resolution estimation. Deformable registration (medical applications)
  • Week 9 (4/3): Moving object detection (background/foreground separation) (Gaussian mixture model, RPCA). Simultaneous estimation of camera motion and moving objects. Object tracking. Video shot segmentation.
  • Programming assignment 5 (Due 4/10): Moving object detection
  • Week 10 (4/10): Stereo and multiview video: depth from disparity, disparity estimation, view synthesis. Depth camera (Kinect). 360 video camera and view stitching. Light field imaging.
  • Week 11 (4/17): Exam
  • Week 12 (4/24): Image representation using unitary transforms (orthogonal bases). Transform coding. JPEG image compression standard. Lecture note
    (updated 4/10/2016Week 11 ( Image representation using wavelet transform; concept of layered coding. JPEG2000 image compression standard. Lecture note

(updated 4/25/2016)

  • Week 13 (5/1): Video coding: block-based motion compensated prediction and interpolation, adaptive spatial prediction, block-based hybrid video coding, rate-distortion optimized mode selection, rate control, Group of pictures (GoP) structure, tradeoff between coding efficiency, delay, and complexity. Lecture note

(updated 4/25/2016)

  • Programming assignment 6 (Due 5/8): Video coding.
  • Week 14 (5/8): Overview of video coding standards (AVC/H.264, HEVC/H.265); Layered video coding: general concept and H.264/SVC. Multiview video compression. 360 Video compression. Error resilience issues. Adaptive Video Streaming (DASH) Lecture note

(updated 5/7/2016)

  • Week 15 (5/15): Project Presentation.
  • 5/20: Project Report and all other material must be uploaded.
January 18, 2017, at 04:57 PM EST by 142.255.110.97 -
Changed lines 76-80 from:

@Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization) @Tutorial on python (Time /location to be arranged) @Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators. @Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.

to:
  • Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)
  • Tutorial on python (Time /location to be arranged)
  • Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.
  • Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
January 18, 2017, at 04:56 PM EST by 142.255.110.97 -
Changed lines 76-79 from:
  1. Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)
  2. Tutorial on python (Time /location to be arranged)
  3. Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.
  4. Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
to:

@Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization) @Tutorial on python (Time /location to be arranged) @Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators. @Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.

January 18, 2017, at 04:55 PM EST by 142.255.110.97 -
Added line 75:
Changed line 79 from:
  1. Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
to:
  1. Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
January 18, 2017, at 04:54 PM EST by 142.255.110.97 -
Changed lines 75-97 from:


to:
  1. Week 1 (1/23): Image Formation and Representation: 3D to 2D projection, photometric image formation, trichromatic color representation, video format (SD, HD, UHD, HDR). Contrast enhancement (concept of histogram, nonlinear mapping, histogram equalization)
  2. Tutorial on python (Time /location to be arranged)
  3. Week 2 (1/30): Review of 1D Fourier transform and convolution. Concept of spatial frequency. Continuous and Discrete Space 2D Fourier transform. 2D convolution and its interpretation in frequency domain. Implementation of 2D convolution. Separable filters. Frequency response. Linear filtering (2D convolution) for noise removal, image sharpening, and edge detection. Gaussian filters, DOG and LOG filters as image gradient operators.
  4. Programming assignment 1 (Due 2/6): Linear filtering for noise removal and image sharpening and illustrating effect in both spatial and frequency domain.
January 18, 2017, at 04:51 PM EST by 142.255.110.97 -
Changed line 82 from:
  1. S16 final exam solution.
to:
  1. S16 final exam solution
Added line 86:

The School of Engineering encourages academic excellence in an environment that promotes honesty, integrity, and fairness. Please see the policy on academic dishonesty: Link

January 18, 2017, at 04:50 PM EST by 142.255.110.97 -
Changed line 77 from:

Sample exams:

to:

Sample exams:

January 18, 2017, at 04:49 PM EST by 142.255.110.97 -
Changed lines 78-82 from:


to:
  1. S15_midterm_w_solution
  2. S15 Final Exam solution
  3. S16_midterm solution
  4. S16 final exam solution.
January 18, 2017, at 04:44 PM EST by 142.255.110.97 -
Changed lines 54-55 from:

Links to resources (lecture notes and sample exams) in previous offerings:

to:

Links to resources (lecture notes and sample exams) in previous offerings:

January 18, 2017, at 04:43 PM EST by 142.255.110.97 -
Changed line 4 from:

Course Description::

to:

Course Description:

Changed line 9 from:

Prerequisites:

to:

Prerequisites:

Changed line 14 from:

Instructor:

to:

Instructor:

Changed line 19 from:

Teaching Assistants:

to:

Teaching Assistants:

Changed line 24 from:

Course Schedule:

to:

Course Schedule:

Changed line 29 from:

Office Hour:

to:

Office Hour:

Changed lines 34-35 from:

Text Book/References:

to:

Text Book/References:

Deleted line 36:
Deleted line 37:
Changed line 41 from:

Grading Policy:

to:

Grading Policy:

Changed line 46 from:

Homework Policy:

to:

Homework Policy:

Changed lines 54-55 from:

Links to resources (lecture notes and sample exams) in previous offerings:

to:

Links to resources (lecture notes and sample exams) in previous offerings:

Changed lines 64-65 from:

Other Useful Links

to:

Other Useful Links

Changed line 76 from:

Sample exams:

to:

Sample exams:

Changed line 79 from:

Policy on Academic Dishonesty:

to:

Policy on Academic Dishonesty:

January 18, 2017, at 04:42 PM EST by 142.255.110.97 -
January 18, 2017, at 04:42 PM EST by 142.255.110.97 -
Changed line 4 from:

Course Description::

to:

Course Description::

January 18, 2017, at 04:41 PM EST by 142.255.110.97 -
Changed line 75 from:

Tentative Course Schedule

to:

Tentative Course Schedule

January 18, 2017, at 04:40 PM EST by 142.255.110.97 -
Changed lines 56-57 from:

Links to resources (lecture notes and sample exams) in previous offerings:


to:

Links to resources (lecture notes and sample exams) in previous offerings:

Changed line 66 from:

Other Useful Links

to:

Other Useful Links

January 18, 2017, at 04:39 PM EST by 142.255.110.97 -
Changed lines 56-57 from:

Links to resources (lecture notes and sample exams) in previous offerings:

to:

Links to resources (lecture notes and sample exams) in previous offerings:


Changed line 66 from:

Other Useful Links

to:

Other Useful Links

January 18, 2017, at 04:39 PM EST by 142.255.110.97 -
Deleted line 58:
Deleted line 59:
Deleted line 60:
Deleted line 61:
Deleted line 62:
Changed lines 68-76 from:
  1. Intro to Python: First three slides of the Python course at Columbia:"Link"
  2. "OpenCV": an open source package including many computer vision algorithms
  3. "Numpy"
  4. "Scipy"
  5. "Matrix Reference Manual"
to:
  1. Intro to Python: First three slides of the Python course at Columbia:Link
  2. OpenCV: an open source package including many computer vision algorithms
  3. Numpy
  4. Scipy
  5. Matrix Reference Manual
January 18, 2017, at 04:37 PM EST by 142.255.110.97 -
Changed line 60 from:
  1. [[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]
to:
  1. EL 6123 Video Processing
January 18, 2017, at 04:36 PM EST by 142.255.110.97 -
Changed lines 58-68 from:
  1. "'EL 5123 Image Processing''
  2. "'[[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]''
  3. "'EL 6123 Image and Video Processing (S16)''
  4. The coursera image processing course by Prof. Katsaggelos:Link
  5. The image processing course at Stanford:"Link"
  6. The computer vision course at U. Washington:"Link"
to:
  1. EL 5123 Image Processing
  2. [[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]
  3. EL 6123 Image and Video Processing (S16)
  4. The coursera image processing course by Prof. Katsaggelos:Link
  5. The image processing course at Stanford:Link
  6. The computer vision course at U. Washington:Link
January 18, 2017, at 04:34 PM EST by 142.255.110.97 -
Deleted line 54:


January 18, 2017, at 04:34 PM EST by 142.255.110.97 -
Changed line 54 from:
 ''Middelbury Stereo Image Database
to:

'''Middelbury Stereo Image Database

January 18, 2017, at 04:33 PM EST by 142.255.110.97 -
January 18, 2017, at 04:33 PM EST by 142.255.110.97 -
Deleted line 52:


Deleted line 53:


January 18, 2017, at 04:32 PM EST by 142.255.110.97 -
Changed line 52 from:

'''Project Guideline'"

to:

'''Project Guideline

Changed line 54 from:

'''Sample Images'"

to:

'''Sample Images

Changed line 56 from:
 ''Middelbury Stereo Image Database'"
to:
 ''Middelbury Stereo Image Database
January 18, 2017, at 04:31 PM EST by 142.255.110.97 -
Changed line 52 from:
 "Project Guideline"
to:

'''Project Guideline'"

Changed line 54 from:
 "Sample Images"
to:

'''Sample Images'"

Changed line 56 from:
 "Middelbury Stereo Image Database"
to:
 ''Middelbury Stereo Image Database'"
January 18, 2017, at 04:30 PM EST by 142.255.110.97 -
Changed lines 61-67 from:
  1. "EL 5123 Image Processing"
  2. "[[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]"
  3. "EL 6123 Image and Video Processing (S16)"
  4. The coursera image processing course by Prof. Katsaggelos:"Link"
to:
  1. "'EL 5123 Image Processing''
  2. "'[[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]''
  3. "'EL 6123 Image and Video Processing (S16)''
  4. The coursera image processing course by Prof. Katsaggelos:Link
January 18, 2017, at 04:30 PM EST by 142.255.110.97 -
Added line 52:
 "Project Guideline"
Changed lines 54-58 from:
 "Project Guideline"


"Sample Images"

to:
 "Sample Images"
January 18, 2017, at 04:29 PM EST by 142.255.110.97 -
Added lines 53-99:
 "Project Guideline"


"Sample Images"


"Middelbury Stereo Image Database"


Links to resources (lecture notes and sample exams) in previous offerings:
  1. "EL 5123 Image Processing"
  2. "[[http://eeweb.poly.edu/~yao/EL6123old/ | EL 6123 Video Processing]"
  3. "EL 6123 Image and Video Processing (S16)"
  4. The coursera image processing course by Prof. Katsaggelos:"Link"
  5. The image processing course at Stanford:"Link"
  6. The computer vision course at U. Washington:"Link"


Other Useful Links

  1. Intro to Python: First three slides of the Python course at Columbia:"Link"
  2. "OpenCV": an open source package including many computer vision algorithms
  3. "Numpy"
  4. "Scipy"
  5. "Matrix Reference Manual"


Tentative Course Schedule


Sample exams:


Policy on Academic Dishonesty:


January 18, 2017, at 04:16 PM EST by 142.255.110.97 -
Changed line 35 from:


to:
Changed lines 37-38 from:



to:
Changed lines 39-40 from:



to:
Changed line 41 from:


to:
January 18, 2017, at 04:15 PM EST by 142.255.110.97 -
Added line 38:


Added line 41:


Added line 44:


Added line 49:


Added line 53:


January 18, 2017, at 04:14 PM EST by 142.255.110.97 -
Added line 8:


Added line 13:


Added line 18:


Added line 23:


Added line 28:


Added line 32:


January 18, 2017, at 04:13 PM EST by 142.255.110.97 -
Changed line 7 from:

//

to:


Changed line 9 from:

//

to:


Changed line 11 from:

//

to:


Changed line 13 from:

//

to:


Changed line 15 from:

//

to:


Changed line 17 from:

//

to:


Changed line 19 from:

//

to:


Changed line 21 from:

//

to:


Changed line 23 from:

//

to:


Changed line 25 from:

//

to:


Changed line 27 from:

//

to:


Changed line 29 from:

//

to:


Changed line 31 from:

//

to:


Changed line 33 from:

//

to:


Changed line 35 from:

//

to:


Changed line 37 from:

//

to:


Changed line 39 from:

//

to:


Changed line 41 from:

//

to:


Changed line 43 from:

//

to:


January 18, 2017, at 04:12 PM EST by 142.255.110.97 -
Added lines 1-43:
Page last modified on February 08, 2018, at 09:00 PM EST