Master Seminar "Visual Feature Learning in Autonomous Driving"
- Preliminary schedule:
- 24.04 : Introduction session
- 30.04 : Topic assignment (online)
- 30.04-15.05 : Collecting materials according to the provided references
- 15.05 : Initial meetings
- 12.06 : Midterm session
- 10.07 : Submission of first drafts (online)
- 17.07,24.07,31.07 : Presentation sessions
- 07.08 : Submission of final reports (online)
- 14.08 : Submission of peer-reviews (online)
- Approach in the seminar:
- Students will be asked to provide either an extensive literature review on the topics, or a detailed comparison between two recent studies in the direction of the topics given below.
- Throughout the seminar, students need to provide a draft report, a final report, a presentation, and a peer-review on one of the reports submitted by peers.
- There will be an introductory session, in which the seminar and the topics will be introduced.
- Please check the preliminary topics below for the seminar.
- Please provide a CV and a motivation letter that states your achievements and aims related to this seminar until the end of 03.02.2019 ( Please send your documents to "emec.ercelik (at) tum.de" with the subject line "Seminar: Visual Feature Learning in Autonomous Driving" ).
- There is no scheduled preliminary session.
- Seminar web page
The ultimate aim of autonomous driving problem is to design self-driving cars that safely and comfortably navigate on the roads without human intervention. Since visual data contains rich information about the environment, this type of data can be utilized for autonomous driving tasks.
In this seminar course, students will investigate different autonomous driving related tasks that involve visual data processing methods. The focus of the given topics are visual feature extraction and learning methods used in the intersection of computer vision and autonomous driving domain.
|Preliminary Topics||Presentation (Date)||Presentation|
- Comparison of LiDAR-based and fusion-based 3D object detection
- Challenges in video object detection and tracking
- Semi-supervised learning for object detection
- Transfer learning with virtual datasets for 3D object detection
- Convolutional recurrent neural networks for object detection and tracking