Tasks
* Analysis of existing BEV architectures with regard to extensibility for variable camera configurations
* Development of a model and a training strategy for heterogeneous camera setups, including scenarios with missing or newly added cameras
* Benchmarking the developed approach on open-source datasets and synthetic data
Requirements
* Degree programs: Computer Science, Artificial Intelligence, Robotics, Automotive Engineering, Data Science or comparable degree program
* Areas of study: Software Development and Programming, Machine Learning and Deep Learning, Computer Vision
* Language skills: English (fluent in spoken and written form); German is an advantage
* Soft skills: High level of initiative; Strong analytical skills; Structured and independent working style; Ability to work in a team; Goal orientation
* Expert knowledge: Experience in machine learning and deep learning; Understanding of sensor data fusion; Fundamentals of camera sensor technology; Fundamentals of 3D data processing
* IT skills: Confident use of MS Office; Solid knowledge of Python, C, or C++
* Experience with Git, Gitlab, and Linux (Ubuntu); Experience with machine learning and AI frameworks (PyTorch, TensorFlow)
#J-18808-Ljbffr