Introduction to Computer Vision

Lecture: Tuesday & Thursday 2:00-3:20 in Sequoyah Hall, Room 148

Discussion: Monday 4:00 – 4:50p, Peterson Hall 104


CSE152 Discussion Board



The course time/location has been moved to Tuesday/Thursday 2:00-3:20 in Sequoyah Hall, Room 148.

Excellent review slides by Tim Marks on linear algebra and random variables online!

The class webboard has been created! It can be accessed here.

The discussion section this week (April 18) has been moved to Will’s office. Please stop by if you have questions!

The reading for Binary Images, Horn Chapters 2 & 3, is here.

Assignment 2 has been posted. A smaller version of the test movie is also available.

Solutions to Assignment 1 have been posted.

Assignment 3 has been posted.

Typos in Assignment 3 (elevation & azimuth for the extra credit problem) have been corrected. Please use the new version!

Will is holding extra office hours on Wednesday May 25 from 1:30pm to 4:30pm. Please come if you need help with the photometric stereo assignment.

The last assignment (Assignment 4) has been posted.

To help you with Assignment 4, you can read the Eigenfaces vs. Fisherfaces paper here.

The due date for Assignment 4 as been postponed to Saturday, June 4 at 5pm.

The final exam will be held on Wednesday, June 8 at 3pm - 6pm in Sequoyah Hall, Room 148.

If you have any questions before the final, please come to Will’s office hours on Monday, June 6.


Instructor: David Kriegman

Office: AP&M 3101

Phone: (858) 822-2424

Email: kriegman@cs.ucsd.edu

Office Hours:  Wednesday 1:30-3:00

TA: Will Chang

Location: AP&M 6313

Email: wychang@cs.ucsd.edu

Office Hours:  Mon 2:00-4:00


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.


            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.





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



Link to lecture notes



Intro to Computer Vision / T&V Chapter 1


Human Visual System


Image Formation, T&V pp.15-19


Color, Color is well-treated in many image-processing texts. Some reasonable on-line sources include: Basics of Color, A FAQ on Color


Segmentation & Binary images, Horn Chapters 2&3, available at e-reserves See on-line resource


Binary Images &/Filtering


Filtering, T&V pp. 55-63


Canny Edge detection, T&V 67-81


Curves, Hough Transforms, T&V, pp. 97-100


Intro to Shape-from-x, Midterm Review




Stereo I,  T&V pp. 140-171


Stereo II


Photometric Stereo ,T&V pp. 140-171


Discrete structure from Motion , T&V pp.195-202, 208-211


Continuous motion T&V pp. 178-194


Optical Flow


Statistical Pattern Recognition, T&V pp. 248, 262-269



Model-based recognition/Final Exam Review, T&V 249-261

Notes and links

1. Programming languages: For this course, all programming will be in Matlab. A short tutorial assignment will provide the introduction   Click here for Serge Belongie’s Matlab resource links.


2.: Some other books and resrouces.

Computer Vision -- A Modern Approach, Forsyth and Ponce, A rather good, upper levelexcellent textbook

An Invitation to 3D Vision: From Images to Geometric Models, Ma, Soatto, Kosecka and Sastry,  Springer Verlag, 2003, ISBN 0-387-00893-4 (textbook for CSE252B)

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

3. Some useful links:

  Camera Calibration Toolbox for Matlab (Bouguet)

  Microsoft Camera Calibration Code (Zhang)

  Intel OpenCV

  The Computer Vision Home Page

  Handy Math reference:   MathWorld

  Related classes at UCSD: CSE 166, CSE252A, CSE 252B

Some other useful vision links