Home
Uni-Logo
 

Computer Vision

Prof. Thomas Brox

Computer vision is a very active research field with many practical applications, for instance in quality control, robotics, driver assistance systems, and many more. The ultimate goal of computer vision is to imitate the great capabilies of the human visual system, allowing the computer not only to record images but also to interpret them. Significant progress has been made in recent years. This course introduces the most important concepts in today's Computer Vision research. The exercises will consist of programming assignments (in C/C++), where you will learn to implement the most important techniques presented in the lectures.

The two former courses Computer Vision I and Computer Vision II have been updated and merged to this single course.

Lecture:
(2 SWS)
Wednesday, 10-12,
Room: SR 01-016, Building 101

Exercises:
(2 SWS)

Friday, 10-12,
Room: SR 00-029, Building 082
Contact persons: Huizhong Zhou, Artemij Amiranashvili

Beginning: Wednesday, October 26, 2016

ECTS Credits: 6
Recommended semester:   1 or 3 (Master)
Requirements: Fundamental mathematical knowledge and programming skills in C++. Image Processing and Computer Graphics teaches important technical knowledge that won't be repeated in Computer Vision. Thus, prior or parallel attendance of Image Processing is highly recommended.
Language and exam: The lectures are given in English. The exam will be an oral exam. Available dates are 16.2., 23.3., and 31.3. The exams take place in room 52-1-29/30.

Motion Segmentation

Slides:

Class 1 (26.10.): Introduction
Class 2 (2.11.): Diffusion filters, TV minimization
Class 3 (9.11.): Image segmentation and combinatorial optimization
Class 4 (16.11.): Spectral clustering
Class 5 (23.11.): Optical Flow I
Class 6 (30.11.): Optical Flow II
Class 7 (7.12.): Video segmentation
Class 8 (14.12.): 3D geometry and camera calibration
Class 9 (21.12.): Stereo reconstruction
Class 10 (11.1.): Disparity estimation and scene flow
Class 11 (18.1.): Structure from motion
Class 12 (25.1.): Object recognition
Class 13 (1.2.): Deep learning for computer vision I
Class 14 (8.2.): Deep learning for computer vision II


Class recordings:

Files are about 200MB each.

Class 1: Introduction
Class 2: Diffusion filters, TV minimization
Class 3: Image segmentation and combinatorial optimization
Class 4: Spectral clustering
Class 5: Optical Flow I
Class 6: Optical Flow II
Class 7: Video segmentation
Class 8: 3D geometry and camera calibration
Class 9: Stereo reconstruction
Class 10: Disparity estimation and scene flow
Class 11: Structure from motion
Class 12: Object recognition
Class 13: Deep learning for computer vision I
Class 14: Deep learning for computer vision II


Exercise material:

Exercise 1: 4.11.
Exercise 2: 11.11.
Exercise 3: (18.11.) Catch up with the previous assignments
Exercise 4: 25.11.
Exercise 5: 2.12.
Exercise 6: (9.12.) Catch up with the previous assignments. Cancelled. Visit the advisor's office during office hours if you have questions.
Exercise 7: 16.12.
Exercise 8: 13.1.
Exercise 9: 20.1.
Exercise 10: (27.1.) Catch up with the previous assignments
Exercise 11: 3.2.
Exercise 12: (10.2.) Catch up with the previous assignments