Organizer: Emec Ercelik

Contact: emec.ercelik (at) tum.de

Modul: IN2107

Registration: Via Matching System

Type: MasterSeminar

Semester: Summer Semester 2021

ECTS: 5.0/4.0

Time & Location: Fridays, 9:00 - 11:00 & Online Sessions via Zoom

• Enrollment to the Moodle is done. I will upload the related documents to the Moodle soon. [12.04.2021]
• Introduction Session on 14.04.2021 at 8:30 in Zoom.
• Registration: Please provide a CV and a couple of sentences about yourself and your motivation related to this seminar until the end of 17.02.2021 ( Please send your documents to "emec.ercelik (at) tum.de" with the subject line "Seminar: Visual Feature Learning in Autonomous Driving" ).
• Schedule:
  • First session - 16.04.2021 (Online meeting)
  • Form a group and select preferred topics - Deadline: 19.04.2021 (via e-mail)
  • Topic assignment - 23.04.2021 (via e-mail)
  • Collecting materials (scientific papers according to the given references) for your report (23.04.2021-07.05.2021)
  • Discussion session: We will discuss the resources found so far - 07.05.2021 (Online meeting)
  • Midterm session: Groups will explain progress - 28.05.2021 (Online meeting)
  • Draft submission to get feedback on the report - Deadline: 18.06.2021
  • Presentation of the findings - 09.07.2021
  • Final submission - Deadline: 23.07.2021
  • Submission of peer-reviews on final reports - Deadline: 06.08.2021
• 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.
• There is no scheduled preliminary session.
• Here, you can find last year's slides of the introductory session.
• You can reach last year's topics here.
• The seminar webpage is here.

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.