Transformer-Based Object Detection with Feedback for Autonomous Driving

Institut

Lehrstuhl für Fahrzeugtechnik

Typ

Masterarbeit /

Inhalt

 

Beschreibung

Autonomous vehicles rely heavily on an accurate representation and understanding of their surroundings. Object detection contributes to this goal by detecting objects of different semantic classes around the ego vehicle.

To improve existing object detection, this thesis explores the impact of motion prediction feedback on object detection. Specifically, by providing approximate information about the intentions of agents around the vehicle, an object detector may enhance its ability to detect these agents. This proposed thesis builds on existing work to optimize the existing architecture and develop alternatives. Specifically, the use of transformer-based architectures should be investigated and evaluated in a representative way.

---

Work packages:

- Literature review on 3D object detectors and trajectory feedback.

- Development of a robust evaluation pipeline

- Development and optimization of the trajectory enhanced object detector

- In-depth evaluation.

 

Keywords: Deep Learning, LiDAR, 3D Object Detection, Motion Prediction, Autonomous Driving

If you are interested, please apply with your CV and transcript of records. 

Voraussetzungen

Requirements:

- Very good programming skills in Python.

- High personal motivation and independent working style.

- Very good language proficiency in German, English or French.

Software

Python

Tags

FTM AV, FTM AV Perception, FTM Stratil, FTM Informatik

Möglicher Beginn

sofort

Kontakt

Loïc Stratil, M.Sc.
Raum: MW 3508
Tel.: +49.89.289.15898
loic.stratiltum.de

Ausschreibung