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 scheduled office hours, you can usually arrange an appointment with the TA or instructor. Just send an email requesting a meeting.

Prerequisites

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

Textbooks

CSE 455 Course Reader, available in the Communications Building, room B042.

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 don't have a CSE account, click here

Grading

• Programming Projects (70%)
• Midterm (15%)
• Final (15%)
• Late projects will be penalized by 33% for each day it is late, and no extra credit will be awarded.  A project due on Friday morning that is turned in on Monday night or Tuesday morning will count two days late (weekends do not count).

Syllabus (tentative)

Image Processing (2 weeks)

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

Image Transformation (2 weeks)

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

Motion Estimation (1 week)

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

Light (1 week)

• physics of light
• color
• reflection
• shading
• shape from shading
• photometric stereo

3D Modeling (3 weeks)

• projective geometry
• camera modeling
• single view metrology
• camera calibration
• stereo

Object Recognition and Applications (1 week)

• eigenfaces
• applications (graphics, robotics)

Last modified 01/05/2006