Computer Vision - CSCI-UA.0480-001

Semester: Spring 2014.

Time and Location: Tuesday and Thursday 11:00-12:15pm, Room 1221, 719 Broadway.

Instructor: Rob Fergus     

Office hours: Thursday 12:15-1:15pm, Room 1226, 12th floor, 719 Broadway.

Grader: Jiali Huang (jh3602@nyu.edu)

Overview

Computer Vision aims to extract descriptions of the world from pictures or video. In recent years, much progress has been made on this challenging problem. The course will start by looking the established area of a geometric vision. It will then move onto mid-level problems such as tracking and segmentation. The final part of the course will focus on recognition, particularly on the problem of detecting object classes (e.g. bottles, shoes, cars) in images, currently a topic much reserach interest.

Prerequisites

The course will be suitable for advanced undergraduates. A reasonable knowledge of linear algebra will be required, along with some basic concepts in machine learning. The homeworks will require Matlab, so familiarity with it is desirable, although not essential.

Assessment

Assessment will be through four graded homework assignments.

Late Policy

The policy regarding late homework is as follows: (a) assignments that are late by less than 24hrs will suffer a 10% reduction; (b) those between 24 and 72 hrs late will suffer a 25%x reduction and (c) those more 72hrs late will suffer a 50% reduction. You are strongly encouraged to start the assignment early and don't be afraid to ask for help from either the TA or myself.

Schedule

Date Time Topics Relevant Book Chapters
WEEK 1
Tues 01/28/2013
11:00-12:15 1. Introduction, Image Formation Pt. 1 Szeliski, Ch. 1 and 2; F & P, Ch. 1
Thur 01/30/2013
11:00-12:15 2. Image Formation Pt. 2 (Slides - PPT) (Slides - PDF)
WEEK 2
Tues 02/04/2013
11:00-12:15 3. Filtering & Edges (Slides - PPT) (Slides - PDF) Szeliski, Ch. 3 and 4; F & P, Ch. 6, 7 and 8
Thur 02/06/2013
11:00-12:15 4. Lighting, Color (Slides - PPT) (Slides - PDF)
WEEK 3
Tues 02/11/2013
11:00-12:15 5. Corner & Region detection. Szeliski, Ch. 3 and 4; F and P, ch. 3 and 16; Lowe 2004
Thur 02/13/2013
11:00-12:15 6. Region representation. (Slides - PPT) (Slides - PDF)

Assignment 1 Out (PDF) (assignment1.zip)
WEEK 4
Thur 02/18/2013
11:00-12:15 7. Fitting, RANSAC (Slides - PPT) (Slides - PDF) Szeliski, Ch. 6; F & P sec. 3.1, ch. 15; Winder and Brown 2007
Thur 02/20/2013
11:00-12:15 8. Image Alignment, Optical Flow
WEEK 5
Tues 02/25/2013
11:00-12:15 9. Epipolar geometry Szeliski, Ch. 7; H and Z, ch. 9-12; F and P, ch. 10 and 11
Thur 02/27/2013
11:00-12:15 10. Stereo reconstruction (Slides - PPT) (Slides - PDF) Szeliski, Ch. 7; H and Z, ch. 9-12; F and P, ch. 10 and 11
WEEK 6
Tues 03/04/2013
11:00-12:15 11. Multiview Stereo, Structure from Motion (Slides - PPT) (Slides - PDF)
Tues 03/04/2013
11:00 Assignment 1 Due

Assignment 2 Out (PDF) (world.txt) (image.txt) (sfm_point.mat) (part4.zip)
Thur 03/06/2013
11:00-12:15 12. Structure from Motion
WEEK 7
Tues 03/11/2013
11:00-12:15 13. Introduction to Recognition. (Slides - PPT) (Slides - PDF)
Thur 03/13/2013
11:00-12:15 14. Specific Object Recognition (Slides - PPT) (Slides - PDF) Szeliski, Ch. 14.
WEEK 8
Spring Break (No class)
WEEK 9
Tues 03/25/2013
11:00-12:15 15. Faces
Thur 03/27/2013
11:00-12:15 16. Recognition - Bag of words models Pt. 1 (Slides - PPT) (Slides - PDF) Szeliski, Ch. 14.
WEEK 10
Tues 04/01/2013
11:00-12:15 17. Recognition - Bag of words models Pt. 2
Tues 04/01/2013
11:00 Assignment 2 Due

Assignment 3 Out (PDF) (faces.zip) (qu2_data.zip)
Thur 04/03/2013
11:00-12:15 18. Recognition - Parts-based models Pt.1 (Slides - PPT) (Slides - PDF)
WEEK 11
Tues 04/08/2013
11:00-12:15 19. Recognition - Parts-based models Pt.2
Thur 04/10/2013
11:00-12:15 20. Neural Networks Part 1 (Slides - PDF)
WEEK 12
Tues 04/15/2013
11:00-12:15 21. Parts and Structure Models Pt. 3 Szeliski, Ch. 5
Thur 04/17/2013
11:00-12:15 22. Segmentation (Slides - PPT) (Slides - PDF)
WEEK 13
Tues 04/22/2013
11:00-12:15 23. Recognition - Boosting (Slides - PPT) (Slides - PDF)
Tues 04/22/2013
11:00 Assignment 3 Due

Assignment 4 Out (PDF)(hw4_qu1.zip) (example_mean_shift.m) (image1.jpg) (tiger.jpg) (baseball.jpg) (Shi and Malik, PAMI 2000)
Thur 04/24/2013
11:00-12:15 24. Recognition - Neural Nets Pt. 2
WEEK 14
Tues 04/29/2013
11:00-12:15 25. Recognition - Neural Nets Pt. 3
Thur 05/01/2013
11:00-12:15 26. Recognition - Neural Nets Pt. 4
WEEK 15
Tues 05/06/2013
11:00-12:15 28. Deep Learning Pt. 1
Thur 05/08/2013
11:00-12:15 27. Deep Learning Pt. 2
EXAM WEEK
Thur 05/15/2013
11:00 Assignment 4 Due (Note that this is a strict deadline)

Acknowledgments

The instructor would like to thank Andrew Zisserman and Svetlana Lazebnik for making their slides available. Thanks also go to Fei-Fei Li and Antonio Torralba for creating the ICCV'05/CVPR'07 object recognition tutorial slides used in classes 11,12,13.

Textbook

The main text book that we will use is:

Szeliski, Richard, Computer Vision: Algorithms and Applications Springer, 2011. This book is available in electronic form at: Link

There are also a couple of other text books relevant to the course, although we won't be directly using them:

Forsyth, David A., and Ponce, J. Computer Vision: A Modern Approach, Prentice Hall, 2003.

Hartley, R. and Zisserman, A. Multiple View Geometry in Computer Vision, Academic Press, 2002.

Both these are available from the CIMS library.

For the object recognition part of the course, please see the Object Reconition Short Course. Link

Additional Material

Matlab guides

Matlab tutorial by Hany Farid and Eero Simoncelli Link

A more comprehensive Matlab tutorial by David Griffiths Link

Further documentation on Matlab can be found here Link

Books

Palmer, Stephen E. Vision Science: Photos to Phenomenology, MIT Press, 1999.

Strang, Gilbert. Linear Algebra and Its Applications 2/e, Academic Press, 1980.

Wandell, Brian A. Foundations of Vision, Sinauer, 1995.