AIFB 04-2022 Bachelor or Master Thesis: Benchmarking Anomaly Detection on Camera and Lidar Data with 3D Voxel Representation

Organisationseinheit

Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)

Ihre Aufgaben

We don’t have autonomous vehicles around us yet because they're not very good at dealing with the many, crazy things we see on the roads of the world. Therefore, anomaly detection is particularly important to detect the unknown and deal with it. In this thesis you will work with a set of state-of-the-art anomaly detection methods, map anomaly scores onto a 3D voxel state and evaluate the results.

The Topic:

• You will implement a set of state-of-the-art anomaly detection methods, such as reconstruction errors, ensembles or Monte Carlo Dropout. Based on a detailed analysis, you will make the selection of the methods to be considered.
• You will use environments and virtual sensor data from the CARLA simulation engine
• The results of the methods, which are either in camera or in lidar space, will be mapped onto a common 3D voxel representation
• You will compare the methods and evaluate thembased on a set of scenarios, which you will choose and design

Eintrittstermin

as soon as possible

Ihre Qualifikation

Your Skills:

• You study Computer Science or a related course of study
• You are deeply interested in topics such as Autonomous Driving, Robotics, Deep Learning or Computer Vision
• You are able to read and write scientific texts in English
• You are fluid in Python, first experiences with PyTorch
• You show an above-average degree of initiative and commitment as well as a thorough way of working