The topics studied in this course will include:
- Image statistics, image representations, and texture models
- Color Vision
- Graphical models, Bayesian methods
- Markov Random Fields, applications to low-level vision
- Approximate inference methods
- Statistical classifiers
- Clustering & Segmentation
- Object recognition
- Tracking and Density Propagation
- Visual Surveillance and Activity Monitoring
| Lecture | Date | Description | Readings | Assignments | Materials |
| 1 | 2/1 | Course Introduction Cameras and Lenses |
Req: FP 1.1, 2.1, 2.2, 2.3, 3.1, 3.2 |
PS0 out | Lecture 1 Lecture 1 (6 slides/page) |
| 2 | 2/3 | Image Filtering |
Req: FP 7.1 - 7.6 |
Lecture 2 Lecture 2 (6 slides/page) Matlab Code Tutorial |
|
| 3 | 2/8 | Image Representations: Pyramids | Req: FP 7.7, 9.2 Handout 1 |
Handout 1 Lecture 3 Lecture 3 (6 slides/page) |
|
| 4 | 2/10 | Image Statistics | Handout 2 | PS0 due |
Handout 2 Lecture 4 Lecture 4 (6 slides/page) |
| 5 | 2/15 | Texture | Req: FP 9.1, 9.3, 9.4 |
PS1 out |
Lecture 5 Lecture 5 (6 slides/page) HeegerBergen Texture Synthesis Code |
| 6 | 2/17 | Color | Req: FP 6.1-6.4 | Lecture 6 Lecture 6 (6 slides/page) |
|
| 2/22 | No class (Presidents Day - Monday class to be held) | ||||
| 7 | 2/24 | Guest Lecture: Context in Vision |
PS1 due | Lecture 7 Lecture 7 (4 slides/page) |
|
| 8 | 3/1 | Local Features for Tracking | Req: Lowe | PS2 out | Handouts 3 - 4 Lecture 8 Lecture 8 (6 slides/page) |
| 9 | 3/3 | Features and Geometry | Req: Mikolajczyk and Schmid; Belongie et al | Handouts 5 - 6 Lecture 9 Lecture 9 - Shape Context Lecture 9 (6 slides/page) Lecture 9 - Shape Context (6 slides/page) |
|
| 10 | 3/8 | Model Based Recognition | Req: FP 18.1-18.5 | Lecture 10 Lecture 10 (6 slides/page) |
|
| 11 | 3/10 | Bayesian Analysis | Req: Ch. 1 of Bishop (handout in class) | PS2 due (Mar. 14 5pm) |
Lecture 11 Lecture 11 (6 slides/page) |
| 12 | 3/15 | Markov Random Fields Belief Propagation |
Req: Jordan and Weiss Opt. Murphy |
EX1 out | Handout 7 Lecture 12 Lecture 12 (6 slides/page) |
| 13 | 3/17 | More on Graphical Models | EX1 due | Lecture 13 Lecture 13 (6 slides/page) |
|
| 3/22-3/24 | Spring Break (NO LECTURE) | ||||
| 14 | 3/29 | More on Graphical Models | Handout 9 Lecture 14 Lecture 14 (6 slides/page) |
||
| 15 | 3/31 | Medical Applications of Computer Vision | Project proposal due PS3 out |
Lecture 15 | |
| 16 | 4/5 | Face Detection and Recognition I | Req: FP 22.1-22.3 |
Lecture 16 Lecture 16 (6 slides/page) |
|
| 17 | 4/7 | Face Detection and Recognition II | Handout 10-12 Lecture 17 Lecture 17 (6 slides/page) |
||
| 18 | 4/12 | Object Recognition | PS3 due | Lecture 18 Lecture 18 (6 slides/page) |
|
| 19 | 4/14 | Segmentation and Clustering | Req: FP 14, 15.1-15.2, Comaniciu and Meer | PS4 out |
Handout 15 Lecture 19 Lecture 19 (6 slides/page) |
| 4/19 | No class (Patriot's Day Holiday) | ||||
| 20 | 4/21 | Computer Vision for Interactive Computer Graphics | Handout 16 Lecture 20 Lecture 20 Part2 Lecture 20 (6 slides/page) Lecture 20 Part2(6 slides/page) |
||
| 21 | 4/26 | Prof. Daniel Huttenlocher's Talk | |||
| 22 | 4/28 | Tracking I | Req: FP 17 |
PS4 due | Lecture 21 Lecture 21 (6 slides/page) |
| 23 | 5/3 | Particle Filters, Tracking humans, | Req: FP Extra Chapter |
EX2 out | Handout 17 Lecture 22 Lecture 22-KTH Lecture 22 (6 slides/page) Lecture 22-KTH (6 slides/page) |
| 24 | 5/5 | Tracking Humans How to Write Papers and Give Talks |
EX2 due | Lecture 23 Lecture 23 (6 slides/page) |
|
| 25 | 5/10 | Applications: Motion Microscopy and Separating Shading from Paint | Lecture 24a Lecture 24b Lecture 24a (6 slides/page) Lecture 24b (6 slides/page) |
||
| 26 | 5/12 | Project Presentations |
Project due | ||
- E. H. Adelson, E. P. Simoncelli, and W. T. Freeman, Pyramids and Multiscale Representations. In Representations of Vision , pp. 3-16, 1991.
- S. Lyu and H. Farid , How Realistic is Photorealistic? . In IEEE Transactions on Signal Processing , 53(2):845-850, 2005.
- D. G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints. In International Journal of Computer Vision , 2004.
- Allan Jepson , Local Feature Tutorial .
- K. Mikolajczyk and C. Schmid, A performance evaluation of local descriptors. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 257-263, 2003.
- S. Belongie, J. Malik and J. Puzicha, Shape Matching and Object Recognition Using Shape Contexts. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 24 , Issue 4 (April 2002), pp. 509 - 522.
- M.I. Jordan and Y. Weiss, Probabilistic inference in graphical models. In Arbib, M. (ed): Handbook of Neural Networks and Brain Theory. 2nd edition. MIT Press, 2002.
- Kevin Murphy, A Brief Introduction to Graphical Models and Bayesian Networks 1998.
- Matlab MRF example codes .
- Baback Moghaddam and Alex Pentland, Probabilistic Visual Learning for Object Representation . In Early Visual Learning, Oxford University Press, 1996.
- B. Moghaddam and M-H. Yang, Gender Classification with Support Vector Machines. In Proceedings of the 4th IEEE Int'll Conf. on Face and Gesture Recognition, 2000.
- B. Moghaddam, T. Jebara and A. Pentland, Bayesian Face Recognition. In Pattern Recognitionn, Vol. 33, No. 11, pps. 1771-1782, November, 2000.
- Bernhard Scholkopf, Statistical Learning and Kernel Methods. In Microsoft Research Technical Report, 2000.
- M. Weber, M. Welling and P. Perona, Unsupervised Learning of Models for Recognition. In ECCV, 2000.
- D. Comaniciu and P.Meer, Mean Shift: A Robust Approach Toward Feature Space Analysis. EEE Transactions on Pattern Analysis and Machine Intelligence, 2002.
- W. Freeman, How to write a conference paper..2002.
- D. Forsyth and J. Ponce, Computer Vision: A Modern Approach, Extra Chapter. Prentice Hall, 2002.
home | syllabus | problem sets and exams | grading and requirements | internet resources
This site is maintained by Xiaoxu Ma.