Computer Vision I
Winter semester 2020/2021
This lecture gives a systematic introduction to computer vision. Exemplary topics include image formation and processing, feature detection and matching, object recognition, motion estimation, structure from motion, stereo, and 3D shape recovery.
Quick links
Course materials (Moodle) – TUCAN
Organization
| Module no. | 20-00-0157-iv |
| Event type | integrated course (IV4, 6CP, 4SWS), elective |
| Being taught | regularly, usually winter semesters |
| Time | Mondays, 13:30 – 17:00 |
| First class |
CV I Live Kickoff & Introduction to Python Monday, 2 November 2020, 13:30 – 15:10 (Kickoff) Monday, 2 November 2020, 15:20 – 17:00 (Python Introduction) For online participation see below (requires login) |
| Location | Digitaler Veranstaltungstermin |
| Lecturer | Prof. Stefan Roth, Ph.D. |
| Assistants | Jan-Martin Steitz, Jannik Schmitt |
| Exam | TBA |
Access restricted section: Log in to see this section.
Content
- Basics of image formation
- Linear and (simple) nonlinear image filtering
- Foundations of multi-view geometry
- Camera calibration and pose estimation
- Foundations of 3D reconstruction
- Foundations of motion estimation from video
- Basics methods for object recognition
- Object classification and detection
- Deep learning for object recognition
- Basics of image segmentation
Learning goals
After successfully attending the course, students are familiar with the basics of computer vision. They understand fundamental techniques for the analysis of images and videos, can name their assumptions and mathematical formulations, as well as describe the resulting algorithms. They are able to implement these techniques in order to solve basic image analysis tasks on realistic imagery.
Degree courses
Can be taken for credit toward BSc / MSc Informatik, MSc Visual Computing, MSc Autonome Systeme, BSc / MSc Computational Engineering and others. Students from other departments, e.g. Mathematik, Elektrotechnik, IST, or Physik are welcome, though academic credit may need to be arranged.
Prerequisites
It is recommended having previously taken Visual Computing (formerly Introduction to Human Computer Systems). Basics in mathematics and probability theory are required.
Literature
|