CS 664 Computer Vision

CS 664 Computer Vision
Cornell University
Fall 2002

THIS IS LAST SEMESTER’S PAGE. IT WILL BE UPDATED NEXT WEEK.

Lectures TR 1:25, 140 Bard.

Professor: Dan Huttenlocher
4133 Upson
Office Hours, Wednesday 2-3pm
dph "at" cs.cornell.edu

TA: Amy Gale
5151 Upson
Office Hours, Friday 1-2pm
amyg "at" cs.cornell.edu

Course materials:

Brief overview:

This course is intended for graduate students and advanced undergraduates who are interested in processing image and video data, in order to extract information about the scene that is being imaged.

We use material from various areas of algorithms and mathematics as well as requiring programming assignments, but do not teach algorithms, mathematics or programming. Thus we expect that students have good programming skills (using C or C++), a good mathematics background, and a knowledge of algorithms. Students will be expected to pick up new mathematical techniques during the semester, as covered in lecture, and to relate the concepts from lecture to the programming assignments.

Here is an outline of the topics to be covered, and the anticipated order of topics:

Uniform local image operations: edge detection, feature detection, multiscale representations. (2 weeks)
Image registration and local image motion estimation (optical flow), use of robust statistical methods. (1-2 weeks)
Image segmentation: perceptual grouping, saliency, image segmentation algorithms. (1-2 weeks)
Determining three-dimensional geometry from multiple two-dimensional images: stereo (feature and area-based methods, relation to motion estimation), structure from motion. (2 weeks)
Determining three-dimensional geometry from intensity: illumination and color models, shape from: specularities, texture, shading, photogrammetry. (1 week)
Two-dimensional image matching and comparison: 2D recognition, correlation, Hausdorff distances, comparing curves. (1-2 weeks)
Learning models from images: appearance models using subspace methods, Hausdorff distances (1-2 weeks)
Extracting models from time-varying images: deformable models (snakes) and tracking. (1 week)
Three dimensional and 2.5 dimensional object recognition and matching: object models, pose recovery, geometric invariants, alignment, search, voting and Hough transforms. (2 weeks)

Course Requirements:

There will be two assignments and a final project. Each of these will require programming, testing with image or video data, and a writeup explaining what was done and why. The programming assignments will be done individually, but the final project may be done in teams of 2 or 3 students. The scope of each final project will depend on the number of students working together.

The programming assignments and project require prior experience with C/C++ on a Unix or Windows platform. (This class will not cover how to use a C development environment to complete the assignments.)