Computer Vision 2
Semester: |
WS 2018 |
Type: |
Lecture |
Lecturer: |
|
Credits: |
None |
Note: This page is for a course from a previous semester.
Find a list of current courses on the Teaching page.
Find a list of current courses on the Teaching page.
News
- We are aware that there are currently some problems with registration for this course in the new rwth online system. We are working to fix them. Please be patient.
Lecture Description
The lecture will cover advanced topics in computer vision. A particular focus will be on state-of-the-art techniques for object detection, tracking, visual odometry and SLAM. There will be regular exercises accompanying the lecture.
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. Some basic material can be found in the following books:
- Computer Vision - A Modern Approach, D. Forsyth, J. Ponce, Prentice Hall, 2002
- Multiple View Geometry, R. Hartley, A. Zisserman, 2nd edition, Cambridge University Press, 2003
- An Invitation to 3D Vision, Y. Ma, S. Soatto, J. Kosecka, S. Sastry, Springer, 2003
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.
Matlab Resources
- Matlab Online Reference Documentation
- Getting started with Matlab
- Techniques for improving performance
- A useful Matlab Quick-reference card (in German).
| Date | Title | Content | Material |
|---|---|---|---|
| Introduction | What is tracking? What is visual odometry? What is SLAM? | ||
| Background Modeling | Simple Background Models, Statistical Background Models, Practical Issues and Extensions | ||
| Template-based Tracking I | Lucas-Kanade Optical Flow, LK Feature Tracking | ||
| Template-based Tracking II | LK Template Tracking, Generalized LK tracking. | ||
| Tracking by Online Classification | Tracking by Online Classification, Boosting for Detection, Extension of boosting to Online Classification | ||
| Tutorial 1: Single-Object Tracking | Tutorial: Background Modelling and Generalized LK Tracking | ||
| Tracking by Detection | Tracking by Detection, Detectors: DPM, VeryFast, Roerei, Faster R-CNN/Mask R-CNN, YOLO... | ||
| - | No Class (Fachschaftsvollversammlung) | ||
| Tracking with Linear Dynamic Models | Tracking with Linear Dynamic Models, Tracking as Inference, Prediction/Correction, Kalman Filter | ||
| Beyond Kalman Filters | Kalman Filter, EKF, Particle Filter | ||
| - | No Class | ||
| Tutorial 2: Bayesian Filtering and Tracking as Prediction | Tutorial: Kalman Filter, EKF, Particle Filter. | ||
| Particle Filters | Particle Filter details | ||
| Multi-Object Tracking I | Data Association, Gating, Global NN, Linear Assignment Problem, Hungarian Algorithm | ||
| Multi-Object Tracking II | MHT, PDAF, JPDAF | ||
| Tutorial 2: Multi-Object Tracking and MHT | Tutorial: Multi-Object Tracking, MHT | ||
| Visual Odometry I | Visual Odometry | ||
| Visual Odometry II | Visual Odometry | ||
| Visual Odometry III | Visual Odometry | ||
| Visual SLAM I | Visual SLAM | ||
| Visual SLAM II | Visual SLAM | ||
| CNNs for Video I | CNNs for Video | ||
| CNNs for Video II | CNNs for Video | ||
| CNNs for Video III | CNNs for Video | ||
| Repetition | Repetition |
