| • | 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 | |
| ￮ | Invariants | ||
| ￮ | Invariant-based recognition algorithms | ||
| ￮ | Image eigenspaces | ||
| ￮ | Introduction to object modeling; shape from single image cues | ||
| Total | 45 hours | ||