Computer Vision
Semester: |
WS 2016 |
Type: |
Lecture |
Lecturer: |
|
Credits: |
V3 + Ü1 (6 ECTS credits) |
Find a list of current courses on the Teaching page.
Type |
Date |
Room |
|---|---|---|
| Lecture | Mon 10:15-11:45 | UMIC 025 |
| Lecture | Wed 10:15-11:45 | UMIC 025 |
Announcement
IMPORTANT: Shift of exam time
Due to the large number of registrations, we had to shift the time for the Computer Vision exam to the following slot:
Friday, 24th of February, 12:00-15:00 (entry ~12:15, exam lasts 2 hours)
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).
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 books: Forsyth &: Ponce: Computer Vision - A Modern Approach
- D. Forsyth, J. Ponce, Computer Vision - A Modern Approach, Prentice Hall, 2002
- R. Szeliski, Computer Vision - Algorithms and Applications, Springer, 2010
- R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, 2nd Edition, Cambridge University Press, 2004
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.
| Date | Title | Content | Material |
|---|---|---|---|
| Introduction | Why vision? Applications, Challenges, Image Formation | ||
| Exercise 1 | Intro Matlab | ||
| Image Processing I | Binary Images, Thresholding, Morphology, Connected Components, Region Descriptors | ||
| Image Processing II | Linear Filters, Gaussian Smoothing, Median Filter | ||
| Edge Detection | Multi-scale Representations, Image Derivatives, Edge Detection | ||
| Structure Extraction | Chamfer Matching, Line Fitting, Hough Transform, Gen. Hough Transform | ||
| Segmentation I | Segmentation as Clustering, k-means, EM, Mean-Shift | ||
| Exercise 2 | Thresholding, Morphology, Derivatives, Edges | ||
| Segmentation II | Segmentation as Energy Minimization, (Markov Random Fields, Graph Cuts) | ||
| Categorization I | Sliding Window-based Object Detection, SVM, HOG | ||
| Categorization II | Haar-Wavelets, AdaBoost, Viola-Jones | ||
| Local Features I | Interest points, Harris Detector, Hessian Detector | ||
| Local Features II | Scale Invariance, Local Descriptors, SIFT | ||
| Exercise 3 | Structure Extraction, Mean-Shift Segmentation, Segmentation with Graph Cuts | ||
| Local Features III | Specific Object Recognition with Local Features, Geometric Verification, Robust Estimation, RANSAC, Gen. Hough Transform | ||
| Matching & Indexing | Matching&Indexing, Visual Vocabularies, Inverted File, Vocabulary Tree, tf-idf Weighting | ||
| Categorization III | Part-Based Methods, Bag-of-Words Model | ||
| Exercise 4 | Histograms, Recognition, Interest Points | ||
| Categorization IV | Deep Learning, CNNs, Large-Scale Visual Recognition with Deep Learning | ||
| Exercise 5 | Interest points, Local Feature Matching, Homography Estimation | ||
| Deep Learning | Deep Learning for other Vision tasks, Segmentation, Face identification, Human Pose Estimation, etc. | ||
| 3D Reconstruction I | Epipolar Geometry, Essential Matrix, Correspondence Search | ||
| 3D Reconstruction II | Camera Parameters, Calibration, Triangulation | ||
| 3D Reconstruction III | Fundamental Matrix, Eight-Point Algorithm, Active Stereo | ||
| Motion & Optical Flow | Motion Fields, Optical Flow, Lucas-Kanade, KLT Tracking | ||
| Exercise 6 | 3D Reconstruction, Eight-point algorithm, RANSAC, Triangulation | ||
| 3D Reconstruction IV | Structure from Motion, Projective Ambiguity, Affine SfM, Factorization, Projective SfM, Euclidean Upgrade, Bundle Adjustment | ||
| Repetition | - | ||
| Exercise Exam | - | ||
| 1st Exam | (AH IV+V) | ||
| Einsicht/Inspection 1st Exam | (UMIC 025) | ||
| 2nd Exam | (AH IV+V) |
