FSCD and BASD: Robust landmark detection and description on radar-based grids

This paper presents a detector and descriptor combination for robust landmarks on grids from radar measurements. Landmarks are fundamental for localization, a task of great importance in the field of mobile robotics and essential for autonomous driving. A fast detector is proposed which uses a rotational invariant pattern to locate scattering centers. These scattering centers occur as local maxima on a measurement grid, where detections from radar sensors for each cell are incremented. For association, a binary version of a descriptor designed especially for radar data is used. Experiments show that for radar data, the proposed combination improves performance compared to state-of-the-art algorithms.