• Homepage
  • Company
  • Jobs
  • Master's Thesis (all genders welcome) - Domain Adaptation with GANs - Image Processing Automated Driving

Master's Thesis (all genders welcome) - Domain Adaptation with GANs - Image Processing Automated Driving AUDI AG

To be filled: 01.12.2018

Work Environment

Audi has long been a driving force in the area of highly-automated driving, and has repeatedly documented its progress in this technology. With the Audi AI traffic jam pilot, they have presented the world's first system with SAE level 3 conditional automation. Already existing driver assistance functions are able to support the driver in different driving tasks, increasing comfort and safety on public roads. 
Those systems require an accurate representation of the car's surroundings. Information about the environment is extracted by various sensors (e.g. radar, lidar, camera). Reliable camera systems with accurate and efficient image processing algorithms are indispensable for the detection of lane markings, traffic signs and other road users.

Job Purpose/Role

Domain adaptation with Generative Adversarial Networks (GANs) allows to transform the domain of images, e.g. illumination and weather conditions, while preserving authentic appearance. The models trained may be used for data augmentation increasing robustness of machine learning techniques or for domain alignment of images captured at different environmental conditions (e.g. day and night) by connected cars. 

The objective of this thesis is to develop artificial intelligence methods for training and evaluation of domain adaptation GANs including the following tasks: 

  • Analysis of related work regarding domain adaptation, especially GAN architectures 
  • Development of architecture and training concepts for multi-domain-transformation 
  • Data management and creation of training and test datasets 
  • Training of GANs for domain adaptation 
  • Visualization as well as qualitative and quantitative evaluation of the results 

    The final objective will be defined in cooperation with the student's university.

Key Requirements/Skills/Experience

  • Master program with a major in informatics, electrical engineering or a comparable field 
  • Theoretical background in machine learning, ideally in GANs 
  • Practical experience in deep learning frameworks (e.g. TensorFlow, PyTorch) is beneficial 
  • Basis knowledge of computer vision (pattern recognition, SLAM, SfM) 
  • Good programming skills (Python, C/C++, Matlab) 
  • Basis knowledge of driver assistance systems and sensors 
  • Enthusiasm for automated driving 
  • Creativity, dedication and the ability to work both in a team and independently

Additional information

Diese Stelle ist bei der AUDI AG in Ingolstadt zu besetzen 

Reference code: I-A-55473

Questions answered by Herr Michael Hofweber 
by calling  +49(0)841-89-38804


Apply now