激光雷达
计算机科学
雷达
人工智能
边距(机器学习)
变压器
雷达成像
计算机视觉
遥感
机器学习
地理
工程类
电信
电气工程
电压
作者
Leichen Wang,Simon Giebenhain,Carsten Anklam,Bastian Goldluecke
标识
DOI:10.1109/lra.2021.3100176
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI