The goal of computer vision is to compute properties of the three-dimensional world from digital images.  Problems in this field include identifying the 3D shape of an environment, determining how things are moving, and recognizing familiar people and objects, all through analysis of images and video.  This course provides an introduction to computer vision, including such topics as feature detection, image segmentation, motion estimation, image mosaics, 3D shape reconstruction, and object recognition.

Notes about office hours:  If it's impossible for you to make it to posted office hours, you can usually arrange an appointment with the TA or instructor. Just send an email requesting a meeting.

Prerequisites

• Data structures, algorithms
• A good working knowledge of C and C++ programming
• Linear algebra
• Vector calculus
• No prior knowledge of vision is assumed.

Textbooks

Forsyth & Ponce, Computer Vision:  A Modern Approach, Pearson, 2002, ISBN 0130851981

We will also use readings from a few textbooks.

Administrative

• Email List:  First get a password reminder (use the Edit Options button at the very bottom of the page), then use the hypermail archive online.
• Computer Accounts:  if you are a non-CSE major, click here.

Grading

• Four programming projects (most of your grade)
• 0-2 (TBD) written homeworks (small percentage)
• No final
• Late projects penalized 33% per day after due date.  Late HW's not accepted.

Syllabus (tentative)

Image Filtering (2 weeks)

• filtering, convolution
• edge detection
• feature detection (corners, lines)
• hough transform
• image pyramids

Image Transformation (2 weeks)

• image warping (parametric transformations, resampling, texture mapping)
• image compositing (alpha blending, color mosaics)
• segmentation and matting (snakes, scissors)

Motion Estimation (2 weeks)

• optical flow
• image alignment
• image mosaics
• feature tracking

3D Modeling (3 weeks)

• projective geometry
• camera modeling
• single view metrology
• camera calibration
• stereo
• structure from motion

Object Recognition and Applications (1 week)

• eigenfaces
• applications (graphics, robotics)

Last modified 04/22/2003