CSE 527
STONY BROOK UNIVERSITY
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
CSE 527: INTRODUCTION TO COMPUTER VISION
TOPICS:
Introduction and Math Review
What is Computer Vision?
Tutorial on Linear Algebra and Matlab
PART I: 2D Vision
Image Formation
Cameras, Lenses, and Sensors
Color and Image Statistics
Appearance-Based Methods
Statistical Linear Models: PCA, ICA, FLD
Non-negative Matrix Factorization, Sparse Matrix Factorization
Statistical Tensor Models: Multilinear PCA, Multilinear ICA
Person and Activity Recognition
Feature Extraction:
Linear filters and edges
Feature extraction (corners and blobs)
Representations: Gaussian Pyramids, Laplacian Pyramids, Steerable Pyramids
Application: face detection
2D Shape Models
Physically Based Models:
o Mass-Spring Systems
o Active Contours (Snakes) - energy minimization, regularization
Statistical Shape Models
Active Shape Models
Active Appearance Models
Kalman Filters
Particle Filters, Condensation
Mean Shift
PART II: 3D Vision
Estimation of 3D Geometry:
Camera calibration, Epipolar Geometry
Stereo, Multi-View Geometry
Shape from Shading
Structure from Motion, Optical Flow
Surface Reconstruction - energy minimization, regularization