Radar Based Object Detection and Tracking for Autonomous Driving

Abstract

Radar sensor has been an integral part of safety critical applications in automotive industry owing to its weather and lighting independence. The advances in radar hardware technology have made it possible to reliably detect objects using radar. Highly accurate radar sensors are able to give multiple radar detections per object. This work presents a postprocessing architecture, which is used to cluster and track multiple detections from one object in practical multiple object scenarios. Furthermore, the framework is tested and validated with various driving maneuvers and results are evaluated.