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

## Fall 2015

Instructor: Ben Ochoa
Email: bochoa at ucsd.edu
Office hours: Th 6:30 PM-7:30 PM, EBU3B 4122

TA: Akshat Dave
Email: akdave at ucsd.edu
Office hours: M 6:00 PM-7:00 PM and W 5:00 PM-6:00 PM, EUB3B 4152

Office hours: M 10:00 AM-12:00 noon, EBU3B B275

Note: when emailing the instructor or one of the TAs with questions about the class, please put "CSE 252A" in the subject line.

Class section ID: 849885
Lecture: TuTh 5:00 PM-6:20 PM, CENTR 212
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 or other programming experience.

Assignments will be prepared using LaTeX. Programming aspects of the assignments will be completed using MATLAB.

Late Policy: Assignments will have a hand-in procedure described with the assignment. Assigments submitted after the due date will incur a 10% per day late penalty. No assignments will be accepted after the graded assignments have been returned or the solutions have been released.

Academic Integrity Policy: Integrity of scholarship is essential for an academic community. The University expects that both faculty and students will honor this principle and in so doing protect the validity of University intellectual work. For students, this means that all academic work will be done by the individual to whom it is assigned, without unauthorized aid of any kind.

Assignments:

• 3D Rotation Matrices and Euler Angles [pdf]
• What Is the Set of Images of an Object under All Possible Illumination Conditions? (Belhumeur and Kriegman) [pdf]
• Decomposition of essential matrix [pdf]
• Introductory Techniques for 3-D Computer Vision, Chapter 8 and Appendix A (Trucco and Verri) [course reserves]
• Planar projective transformation, 4 point to standard projective basis [pdf]
• Planar projective transformation, 4 point [pdf]

Lecture slides:

Lecture topics (tentative):

• Introduction to computer vision
• Geometric image formation, Chapter 1
• Photometric image formation, Chapter 2
• Photometric stereo, Section 2.2.4
• Uncalibrated photometric stereo
• Filtering, Chapter 4
• Edges and corners, Chapter 5
• Stereo, Chapter 7
• Helmholtz stereo
• Structure from motion, Chapter 8
• Model fitting, Chapter 10
• Optical flow and motion, Sections 10.6.1 and 10.6.2
• Tracking, Chapter 11
• Recognition, detection, and classification, Chapters 15-17
• Color, Chapter 3
• Human visual system, Section 1.1.4

Required textbook:

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

Computer Vision: Algorithms and Applications
Richard Szeliski
Springer, 2011