CSE190-B

Introduction to Computer Vision

Tuesday, Thursday 3:30-4:50

Warren Lecture Halls, Rm. 2205

http://www-cse.ucsd.edu/classes/sp03/cse190-b/

Discuss CS 190-B Discussion

Class Mailing list: cse190-b@cs.ucsd.edu

Announcement: Final Exam, Thursday, June 12, 3:00-6:00, WLH 2205.

Instructor: David Kriegman

Office: AP&M 3101

Phone: (858) 822-2424

Email: kriegman@cs.ucsd.edu

Office Hours: Wednesday1:00-2:30

TA: Diem Vu

Location: AP&M 3349D

Email: d1vu@cs.ucsd.edu

Office Hours: Tuesday11:00-12:30, Thursday 10:00-11:00

Class Description: The goal of computer vision is to compute properties of the three-dimensional world from images and video.Problems in this field include identifying the 3D shape of a scene, determining how things are moving, and recognizing familiar people and objects.This course provides an introduction to computer vision, including such topics as feature detection, image segmentation, motion estimation, object recognition, and 3D shape reconstruction through stereo, photometric stereo, and structure from motion.4 units.

Required Text: Introductory Techniques for 3-D Computer Vision, E. Trucco and A. Verri, Prentice Hall, 1998.

Prerequisites: Linear algebra and Multivariable calculus (e.g., Math 20A & 20F), data structure/algorithms (e.g., CSE100), a good working knowledge of C,C++, or Matlab programming.

Grading:

Assignments: 45%

Midterm:  20%

Final Exam: 35%

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.

Assignments

• Assignment 1: [pdf] [ps]   Test images and C routine can be found here. Submit your assignment by email to d1vu@cs.ucsd.edu
  Matlab availabitlity at UCSD
  Sample solution for problem 1 in Matlab. label.m and locate.m
  Assignment 1 result

• Assignment 2, Due May 1[pdf] [ps]   Test images are here.
  Answer key[PDF][PS]

• Assignment 3, Due May 27[pdf] [ps]   Test images are here.

• Assignment 4, Due June 5[pdf] [ps]   Test images are here.

---

Syllabus

[ Note that this Syllabus is tentative & subject to change]

Week	Date/ Link to lecture notes	Topic/Readings
1	Apr. 1	Intro to Computer Vision / T&V Chapter 1
	Apr. 3	Human Visual System
2	Apr. 8	Image Formation, T&V pp.15-19
	Apr. 10	Color, Color is well-treated in many image-processing texts.Some reasonable on-line sources include: Basics of Color, A FAQ on Color
3	Apr. 15	Segmentation & Binary images, Horn Chapters 3&4, available at e-reserves See on-line resource
	Apr. 17	Binary Images &/Filtering
4	Apr. 22	Filtering, T&V pp. 55-63
	Apr. 24	Canny Edge detection, T&V 67-81
5	Apr. 29	Curves, Hough Transforms, T&V, pp. 97-100
	May 1	Intro to Shape-from-x, MidtermReview
6	May 6	Midterm
	May 8	Photometric Stereo ,T&V pp. 140-171
7	May 13	Stereo I, T&V pp. 140-171
	May 15	Stereo II
8	May 20	Epipolar Geometry
	May 22	Discrete structure from Motion , T&V pp.195-202, 208-211
9	May 27	Optical Flow, T&V pp. 178-194
10	June 3	Statistical Pattern Recognition, T&V pp. 248, 262-269
	June 5-1	Appearance-based recognition, “Finding Templates Using Classifiers”, Forsyth & Ponce
	June 5-2	Model-based recognition/Final Exam Review, , T&V 249-261

Notes and links

Programming languages:For any work in this course, you can use any language.We’ve often found it convenient to program many image operations in Matlab. . Click here for Serge Belongie’sMatlab resource links.

Another excellent textbook: Computer Vision -- A Modern Approach, Forsyth and Ponce

CV-online: A useful on-line compendium of Computer Vision sources

Handy Math reference:MathWorld

Some other useful vision links