16-385 Computer Vision

Carnegie Mellon University

Spring 2013 School of Computer Science

Course Description

An introduction to the theory and practice of computer vision, i.e. the analysis of the patterns in visual images with the view to understanding the objects and processes in the world that generate them. Major topics include optics, image representation, feature extraction, image processing, object recognition, feature selection, probabilistic inference, perceptual analysis and organization, dynamic and hierarchical processing. The emphasis is on the learning of mathematical concepts and techniques and the translation of them to Matlab programs to solve real vision problem. The discussion will be guided by comparision with human and animal vision, from psychological and biological perspectives. Prerequisites: 15-100, 21-120 or permission of instructor. 21-241 preferred but not required.

Course Information

Instructors	Office (Office hours)	Email (Phone)
Tai Sing Lee (Professor)	Mellon Inst. Rm 115	tai@cnbc.cmu.edu
	GHC 8017 (M 2-3 p.m. 3:05-4:45 pm)
Hatem Alismail	Wed 7-8 GHC 5th floor open area	halismai@cs.cmu.edu

* Time and Place of Office Hours subject to change.

Class location and time: DH 1212 Tuesday, Thursday 10:30 a.m - 11:50 a.m.
Website: http://www.cnbc.cmu.edu/~tai/cv13.html (course schedule and basic info)
Blackboard: http://www.cmu.edu/blackboard/

Classroom Etiquette

Please turn OFF your laptop, cell phones or any other electronic devices in the classroom or you will be asked to leave the classroom. Thank you.

Grading Scheme

Evaluation	% of Grade
5 Assignments	50
Quiz 1	10
Term Project	25
Quiz 2	15

Homework Assignments

Homework report should be type-written. You should submit a hardcopy, documenting all the answers and results, in class on the due day. You should also submit a softcopy of write-up and the codes to Blackboard before 10:00 a.m. on the due day. Blackboard submission after 10:00 a.m. is considered late.
You are allowed to collaborate in certain specified parts of the first two assignments and in the term project. Each should submit a copy of the solution, but should list his/her partner, if any, on the first page of the report.

Late Policy

Each student has ONE chance to turn in one of five the homework assignments late within one week without penalty.
If you need to submit a late homework after using the one free late, you will receive a 5 percent deduction of your earned homework credit every two days, until the solution set is released.
No extension possible for the term project.

Term project

The term project of your own design. There are however more structured competiton challenges we could suggest. You should talk to the instructor and TA to come up with a project earlier in March. You will need to submit a proposal (worth 5 points), with motivation and background and preliminary data, to get approval.
The projects will be presented in oral presentation session and/or a poster session. Your fellow students will participate in voting for best projects.

Examinations

There will be two quizzes to test understanding of the materials covered and discussed in the lectures.

Final Grade Assignment

A for total grade >= 88 %, B: < 88 AND >= 75, C: < 75, >=60. F for cheating.

Syllabus

* Relevant Reading: Richard Szeliski, Computer Vision: Algorithms and Applications . Springer, 2010.

Date	Lecture Topic	Relevant Readings	Assignments/Help Sessions
	IMAGE AND FEATURE REPRESENTATION
T 1/15	1. Introduction to computer vision	ch. 1
R 1/17	2. Image and Fourier Representation	ch 3.4	HW 1 out. ;
T 1/22	3. Optics and Image Formation	ch 2.2, 2.3
R 1/24	4. Camera and Calibration	ch 2.1, 2.2, 6.3.1, 6.3.5
T 1/29	5. Linear Filters	ch 3.1, 3.2	HW 1 in. HW 2 out.
R 1/31	6. Laplacian pyramid	ch 3.5
T 2/5	6. Image Blending	ch 3.5
R 2/7	7. Wavelets	ch 3.5
T 2/12	8. Principal component analysis	Appendix A.1 Ch. 14.2.1
R 2/14	9. Independent Components	Handouts	HW 2 due, HW 3 out.
	OBJECT AND SCENE RECOGNITION
T 2/19	10. Simple Features and boosting	Ch 4.2, 4.3, 5.1.1
R 2/21	10. Face detection and cascades	ch 14.1
T 2/26	11. Pattern Descriptors (SIFT and HOG)	ch 4.1, 14.1
R 2/28	12. Classification (SVM and KNN)	ch 14 and handout	HW 3 in. HW 4 out
T 3/5	13. LDA (Linear Discriminant)	ch 14.2
R 3/7	Quiz 1 (up to Lecture 11)		Project ideas
M 3/11	Midterm Grade due 6 p.m.
T 3/12	Spring break
R 3/14	Spring break
	PERCEPTUAL INFERENCE
T 3/19	14. Optical flow	ch 8.4
R 3/21	15. Motion Analysis	ch 8.5	HW 4 in. HW 5 out
T 3/26	16. Tracking	ch 4.1, 5.1 and handouts
R 3/28	17. Structure from motion	Ch 7.1, 7.2
T 4/2	18. Shape from shading	Ch 12.1.1
R 4/4	19. Odometry and Pose Estimation	Ch 6.2	HW 5 due
T 4/9	20. Active Shape and Appearance model	Ch 14.2.2
R 4/11	21. Scene Recognition	Handouts ;
T 4/16	22. Coherent scene interpretation	handouts	Project midterm (3)
R 4/18	Spring Carnival
T 4/23	23. Segmentation (MRF, Mean shift, Graphcut)	Ch 5.3, 5.4, 5.5
R 4/25	24. Review	handouts
T 4/30	25. Review and Hierarchy
R 5/2	Quiz 2
W 5/8	Project Deadline		All term papers and projects due.
S 5/11	Project Presentation
R 5/16	Final Grade due 6 p.m.

Questions or comments: contact Tai Sing Lee
Last modified: Jan. 2013 Tai Sing Lee