DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
UNIVERSITY OF CALIFORNIA, SAN DIEGO

## Fall 2014

Instructor: Ben Ochoa
Email: bochoa at ucsd.edu
Office hours: Tu 6:30 PM-7:30 PM

TA: Sam Kwak
Email: iskwak+252a at cs.ucsd.edu
Office hours: MW 4:00 PM-5:00 PM, EBU3B 4127

Note: when emailing the instructor or TA with questions about the class, please put "CSE252A" in the subject line.

Class section ID: 824418
Lecture: TuTh 5:00 PM-6:20 PM, PETER 103
Class discussion: Piazza

This course provides a comprehensive introduction to computer vision providing broad coverage including low level vision (image formation, photometry, color, image feature detection), inferring 3D properties from images (shape-from-shading, stereo vision, motion interpretation) and object recognition.

Prerequisites: Linear algebra, calculus, probability and statistics. Matlab, Python, C/C++, or other programming experience.

Assignments should be prepared using LaTeX. Programming aspects of the assignments will be completed using either Matlab or Python.

Late Policy: Written homework will be due in class and accepted thereafter with a penalty of 10% per day starting from the due date. Programming assignments will have a hand-in procedure described with the assignment, and also has a 10% per day late penalty. No assignments will be accepted after the graded assignments have been returned or the solutions have been released.

Collaboration Policy: You may work together on homework assignments to discuss ideas and methods only, however what you turn in should be your own work and any code should be your own coding. Copying is not permitted.

Assignments:

Lecture slides:

Lecture topics (tentative):

• Intro to Computer Vision
• Human Visual System, F&P sec. 1.3. RS 1-18
• Image Formation and Cameras. Projective Geometry. Homogeneous Coordinates. Homography
• Homography. Perspective, Affine, orthographic projection and geometry. Camera Models. Lenses
• 4-point planar projection transformation calculation Trucco and Verri, pp. 316-318
• Lenses Continued. SO(3) Transformations. Radiometry (Irradiance, Radiance, BRDF), F&P Chapter 4
• Radiometry Continued. Radiance and Irradiance. Special BRDF's, Light Sources, Photometric Stereo.
• Lighting and Photometric Stereo F&P Section 2.2
• Photometric Stereo F&P Section 2.2
• Illumination Cones, Belhumeur, Kriegman, What Is the Set of Images of an Object under All Possible Illumination Conditions?, IJCV 28(3), 1998, 245-260
• Color, Dichromatic model, RS 67
• Color, Dichromatic Model Continued. SUV Space. Filtering F&P Chap. 7, 8, RS. 101-1.22
• Edges RS 238-249
• Epipolar Constraint and Stereo I, F&P Sec. 10.1, RS 530-544
• Stereo II, Dynamic Programming, Chapter 11, 545-548, 552-556
• Optical Flow, Trucco and Verri, pp. 178-194, RS 4381-414
• Infinitesimal structure from Motion, Trucco and Verri pp. 195-202, 208-211
• Tracking, F&P Chap.17, RS 235-237, 282-284, 551-552, 605-609
• Statistical Pattern Recognition, F&P 22.1-22.3
• Support Vector Machines & Kernel Methods, F&P Sec. 22.5, 22.8
• Appearance-based Recognition and Model-based recognition, F&P Chap. 18, RS 655-722

Required textbook:

Computer Vision: A Modern Approach, 2nd edition
David A. Forsyth and Jean Ponce
Prentice Hall, 2011
[Amazon]

Supplemental textbook:

Computer Vision: Algorithms and Applications
Richard Szeliski
Springer, 2011

Introductory Techniques for 3-D Computer Vision
Emanuele Trucco and Alessandro Verri
Prentice Hall, 1998
[Amazon]
(textbook for CSE 152)

Multiple View Geometry in Computer Vision, 2nd edition
Richard Hartley and Andrew Zisserman
Cambridge University Press, 2004
[Cambridge Books Online] [Amazon] [Google]
(textbook for CSE 252B)

Last update: December 11, 2014