Radar Ghost Target Detection via Multimodal Transformers

作者：Leichen Wang, Simon Giebenhain, Carsten Anklam, Bastian Goldlüecke · 发表于：IEEE Robotics and Automation Letters · 年份：2021 · DOI：10.1109/lra.2021.3100176 · 被引用次数：27 · 研究领域：Geophysical Methods and Applications、Advanced SAR Imaging Techniques、Microwave Imaging and Scattering Analysis

Ghost targets caused by inter-reflections are by design unavoidable in radar measurements, and it is challenging to distinguish these artifact detections from real ones. In this letter, we propose a novel approach to detect radar ghost targets by using LiDAR data as a reference. For this, we adopt a multimodal transformer network to learn interactions between points. We employ self-attention to exchange information between radar points, and local crossmodal attention to infuse information from surrounding LiDAR points. The key idea is that a ghost target should have higher semantic affinity with the reflected real target than the other ones. Extensive experiments on nuScenes [1] show that our method outperforms the baseline method on radar ghost target detection by a large margin.