Feature Extraction of Extended Objects using Multiple Autmotive Radar Sensors

Future advanced driver assistant systems not only will use information of multiple sensor types, but also employ multiple sensors of the same kind. This will be especially true in the case of automotive radar sensors, which when combined into a radar sensor network, allow for extended features like 360 degree coverage around the ego vehicle or the extraction of additional information of the other vehicles in the scenario.

In this thesis, new algorithms are to be developed to extract properties like width, length, orientation, and motion of other vehicles in an automotive setting scenario with the help of a network of multiple radar sensors. This allows for directly extracting the full motion information of observed vehicles as well as improved stability of classic estimation methods by exploiting different viewing angles and extended coverage. The algorithms will be improved and validated with real-life measurement data.