This new project gives you the chance to learn about current computer vision topics and get practical experience in the field during the exercises. In this semester, the project covers the following topics:

1. Image processing of distance images
2. Camera calibration and projective geometry
3. Stereo vision and RGB-D imaging
4. Image superresolution (subject to change)
5. Image retrieval / classification

Organization

During the semester lecture and exercise alternate on a weekly basis. Exercises are supervised and take place in one of the CIP pools. All exercises must be completed. For 10 ECTS credits you are required to implement a state-of-the-art/recently published algorithm selected from one of the topics above.

• Lectures will take place in 00.152
• The exercises will talk place in 0.01-142 (Casa Huber), same time as above.

Credits

You can get either 5 or 10 ECTS credits for this project. The following options are available:

5 ECTS (counts as: Hochschulpraktikum):

• lectures
• exercises (in groups of 2-3 people) to be finished and presented until the end of regular schedule
• individual presentation about a state-of-the-art research paper at the end of the semester (graded if needed)

10 ECTS (counts as Hochschulpraktikum (5ECTS) + Forschungspraktikum (5ECTS), or Master Project Computer Science (10ECTS))

• lectures
• exercises (in groups of 2-3 people) to be finished and presented until the end of regular schedule
• individual coding/research project under supervision of a LME PhD student at the end of regular schedule (graded if needed)

Slides and exercises are available in StudOn. You can join the course on this website.