Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection

arXiv:2403.01978v1 Announce Type: new
Abstract: 3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity in training sample allocation based on box Intersection over Union (IoU_box). This problem impedes further enhancements in the performance of anchor-based LiDAR 3D object detectors. To tackle this challenge, this paper introduces a new training sample selection method that utilizes point …

3d object 3d object detection anchor arxiv cs.cv detection lidar sample type via