Computer Vision WS 09/10
News
- There will be no lecture on Tuesday, 03.11. (DIES Fachschaftsvollversammlung)!
- Please note that the Tuesday lecture slot had to be moved to 12:30-14:00. This became necessary in order to get a sufficiently large room to seat the unexpectedly large number of participants.
- If you haven't already done so, please subscribe to the lecture on the Campus website in order to obtain important email announcements during the course of the lecture.
Overview
| Lecturer: | Prof. Dr. Bastian Leibe |
| Teaching Assistant: |
Tobias Weyand |
| Lecture type: | V3 + Ü1 (6 ECTS credits) |
| When & Where: | Tue 12:30-14:00, UMIC 025 Thu 13:15-14:45, UMIC 025 Directions to UMIC |
| Content: | see below |
| Literature: | see below |
Lecture Description
Cameras and images form an ever-growing part of our daily lives. Billions of images and massive amounts of video data are becoming available on the Internet. Large search engines are being created to make sense out of this data. And more and more commercial applications are coming up, e.g. in surveillance and security, on consumer devices, for video special effects, in mobile robotics and automotive contexts, and for medical image processing. All those applications are building on visual capabilities. For us humans, those capabilities are natural. But how do we actually accomplish them? And how can we teach a machine to perform similar tasks for us?The goal of Computer Vision is to develop methods that enable a machine to "understand" or analyze images and videos. This lecture will teach the fundamental Computer Vision techniques that underlie such capabilities. In addition, it will show current research developments and how they are applied to solve real-world tasks. The lecture is accompanied by Matlab-based exercises that will allow you to collect hands-on experience with the algorithms introduced in the lecture (there will be one exercise sheet roughly every two weeks).
Tentative Schedule
| Date |
Topic |
Content |
Slides |
Related Material |
|---|---|---|---|---|
| 13.10.09 | no class | - | - | - |
| 15.10.09 | Introduction | Why vision? Applications, Challenges, Image Formation |
pdf, fullpage |
|
| 20.10.09 | no class (UMIC Day) | - | - |
- |
| 22.10.09 | Image Processing I | Binary Images, Thresholding, Morphology, Connected Components, Region Descriptors |
pdf, fullpage | |
| 27.10.09 | Image Processing II | Linear Filters, Gaussian Smoothing, Image Derivatives, Multi-scale Representations | pdf, fullpage | F&P chapters 7, 8 Haribo Classification Demo |
| 29.10.09 | Exercise 1 | Intro Matlab, Thresholding, Morphology | exercise1.pdf exercise1.zip solutions1.zip slides |
Matlab resources |
| 03.11.09 | no class (Fachschaftsvollvers.) |
- |
||
| 05.11.09 | Structure Extraction | Edge Detection, Chamfer Matching, Line Fitting, Hough Transform, Gen. Hough Transform | pdf, fullpage |
B&B on the Generalized HT, Hough Transform demo |
| 10.11.09 | Color | Radiometry, Color Perception, Color Spaces, Skin Detection | pdf, fullpage |
|
| 12.11.09 | Exercise 2 | Derivatives, Edges, Hough Transform | exercise2.pdf exercise2.zip solutions2.zip |
|
| 17.11.09 | Recognition I | Global Descriptors, Histograms, Histogram Comparison, Backprojection, Multidim. Histograms, Prob. Recognition | pdf, fullpage |
Schiele&Crowley paper |
| 19.11.09 | Segmentation I | Grouping Principles, Segmentation as Clustering, k-means, Mean-Shift | pdf, fullpage |
F&P chapter 14, Max Wertheimer's Gestalt Laws |
| 24.11.09 | Exercise 3 | Histogram-based Recognition, Mean-Shift Segmentation |
exercise3.pdf exercise3.zip |
|
| 26.11.09 | Segmentation II | Graph-theoretic Segmentation, Segmentation as Energy Minimization, Markov Random Fields, Graph Cuts | ||
| 01.12.09 | Recognition II |
Subspace Representations, PCA, Eigenfaces, LDA, Fisherfaces, Robust PCA | ||
| 03.12.09 | Categorization I | Sliding Window-based Object Detection, Haar-Wavelets, AdaBoost, Viola-Jones, SVM, HOG | ||
| 08.12.09 | Exercise 4 |
Object Recognition: Eigenfaces, Fisherfaces, Viola-Jones Face Detection |
|
|
| 10.12.09 | Local Features I | |||
| 15.12.09 | Local Features II | |||
| 17.12.09 | Categorization II | |||
| 22.12.09 | Exercise 5 | Interest points, Local Feature Matching, Homography Estimation |
|
|
| 07.01.10 | Categorization III | |||
| 12.01.10 | 3D Reconstruction I | |||
| 14.01.10 | 3D Reconstruction II | |||
| 19.01.10 | Exercise 6 | 3D Reconstruction: Eight-point algorithm, RANSAC, Triangulation |
||
| 21.01.10 | 3D Reconstruction III | |||
| 26.01.10 | Motion & Tracking I | |||
| 28.01.10 | Motion & Tracking II | |||
| 02.01.10 | Exercise 7 |
Tracking |
||
| 04.02.10 | Repetition |
Literature
In the last decades, Computer Vision has evolved into a rapidly growing field with research going into so many directions that no single book can cover them all. We will mainly make use of the following two books:
![]()
D. Forsyth, J. Ponce
Computer Vision -- A Modern Approach,
Prentice Hall, 2002
However, a good part of the material presented in this class is the result of very recent research, so it hasn't found its way into textbooks yet. Wherever research papers are necessary for a deeper understanding, we will make them available on this web page.
Additional Resources
- Ballard & Brown's classic book "Computer Vision" from 1982 is now available online.
Matlab Resources
-
The Matlab Primer
-
A useful Matlab Quick-reference card (in German).
Contact
For all questions concering the lecture, please contact
Tobias Weyand
