Projekt Computer Vision [ProjCV]
The goal of this master project is to build state-of-the-art software for different advanced topics in computer vision. During the project you will learn about basic image processing methods, the foundations of projective geometry, 3D cameras, super-resolution, tracking, feature detection and classification. The project is designed to be completed in two parts: In the first part, the basics of each topic will be developed in a group. All participants will create basic tools for certain computer vision applications. The following topics will be taught and implemented during the first part: - Basic image processing of grayscale and distance images - Pinhole camera and projective geometry - Stereo vision and RGB-D imaging - Super resolution - Image retrieval / Image classification In the second part each participant will implement a method which belongs to one of the aforementioned topics. We will provide data or evaluation setups which allow you to test your own implementations.
Dates & Rooms:
Monday, 12:00 - 14:00; Room: 0.01-142
This project gives you the chance to learn about current computer vision topics and get practical experience in the field during the exercises. The project covers the following topics:
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.
You can get either 5 or 10 ECTS credits for this project. The following options are available:
5 ECTS (counts as: Hochschulpraktikum)
This option requires:
10 ECTS (counts as Hochschulpraktikum (5 ECTS) + Forschungspraktikum (5 ECTS), or Master Project Computer Science (10 ECTS))
Important: You cannot use the lecture/exercise part as a 5 ECTS research project (Forschungspraktikum). Please contact one of the PhD students at the lab if you need a research project.