This is an archived page and may be obsolete; the current pages are at

CS 512: Computer Vision




Introduction 1.5 hours
Overview of computer vision, related areas, and applications
Feature extraction 4.5 hours
Detection of edges in images
Canny edge detector
Detection of corners
Harris corner detector
Probabilistic modeling 4.5 hours
Review of probability and Bayes' theorem
Principles of probabilistic modeling
Estimation paradigms
Maximum likelihood estimation (MLE)
Bayesian estimation
Camera calibration 4.5 hours
Camera models
Intrinsic and extrinsic parameters
Radial lens distortion
Direct parameter calibration
Camera parameters from the projection matrix
Epipolar geometry 4.5 hours
Introduction to projective geometry
Epipolar constraints
The essential and fundamental matrices
Statistical estimation 4.5 hours
The Expectation-Maximization (EM) algorithm
Implementation issues
EM variants
Model reconstruction 4.5 hours
Reconstruction by triangulation
Reconstruction up to a scale factor
Reconstruction up to a projective transformation
Statistical filtering 4.5 hours
Iterated estimation
Observability and linear systems
The Kalman Filter
The Extended Kalman Filter
Motion Estimation 6.0 hours
Motion field of rigid objects
Motion parallax
Optical flow
The image brightness constancy equation
Differential techniques
Feature-based techniques
Recognition 6.0 hours
Invariant-based recognition algorithms
Image eigenspaces
Introduction to object modeling; shape from single image cues
Total 45 hours

Edited March 2006 (html, css checks)