Uni-Logo
You are here: Home Teaching SS 2015 Robotik Praktikum (Parking space detection)
Artikelaktionen

Practical Course - SS 2015

Parking Space Detection -- Robotik Praktikum / Robotics Practical Course

Topic

This practical course will address the problem of detecting free and occupied parking spaces for autonomous cars or driver assistance systems. We will consider two scenarios: initially, we will focus on detecting marked parking areas from overhead aerial images such as google maps satellite images using 2D image analysis tools. In a second step, we will combine this information with 3D point cloud data acquired with a real robot to identify free parking spaces. Furthermore, we will use the resulting segmentation to learn a classifier for cars based on 3D features. Finally, the goal is to fuse the results of both classifiers to improve the map over time.

A practical course (Praktikum) is a hands-on experience including a significant amount of programing work. The students will work in small teams and are requested to plan the project as a whole and to coordinate their actions. Furthermore, the students are expected to support their team throughout the whole term. Basic programming skills in C/C++ are required for this course. More details will be provided in the first meeting.

Organization

  • Organizers: Maxim Tatarchenko, Barbara Frank, Prof. Dr. Wolfram Burgard
  • The course takes place Tue, 14-16 in building 079, SR 00-019. The first meeting is on Tue, Apr 28, 14h (ct).
  • ECTS-points: 6 (This corresponds to approximately 15 hours workload per week during the lecture period.)
  • Examination: Students are required to actively participate in the development of the software within their team, to actively participate in the course and to regularly present intermediate results and milestones. At the end of the semester, the students will present their developed system.
  • Teaching is done in English (or German depending on the participating students).

Slides

Additional Material

  • Example programs from the tutorial as well as example data sets will be provided in the svn repository. Please contact us for access details.

Some Potentially Useful Links

Further Reading

  • Houben, S., Komar, M., Hohm, A., Lüke, S., Neuhausen, M., & Schlipsing, M.. On-Vehicle Video-Based Parking Lot Recognition with Fisheye Optics. In Proceedings of the IEEE Annual Conference on Intelligent Transportation Systems, 2013 (Paper)
  • Tschentscher, M., & Neuhausen, M.. Video-based Parking-space Detection. In Proceedings of the Forum Bauinformatik (pp. 159-166), 2012 (Paper)
Benutzerspezifische Werkzeuge