PDANet: Point Distribution Awareness for 3D Object Detection from Lidar Point Clouds

Recent deep learning models for 3D object detection based on lidar point clouds have exhibited promising performance in the detection of on-road objects. However, their performance is often constrained when detecting small objects like pedestrians and cyclists. Due to occlusions and their inherent volumes, the spatial and semantic information of small objects is relatively limited. Therefore, we propose a Point Distribution Awareness Network (PDANet) that emphasizes the structural distribution of objects, to enhance the extraction of positional, geometric, and semantic features. It comprises two modules: a multi-feature adaptive perception (MFAP) module, enhancing local feature perception, and a semantic-aware downsampling module, enhancing the selection of foreground points. These modules can be used in a plug-and-play manner for point downsampling feature perception. They are then integrated as a branch into representative point-based (IA-SSD), point-voxel-based (PV-RCNN), and voxel-based (Centerpoint) detectors, resulting in PDA-SSD, PDA-PV-RCNN, and PDA-CenterPoint models. Through experiments on the ONCE dataset, the PDANet brought up the mAP of all three types of baseline models by 3.03%, 4.60%, and 6.15%, respectively. Further experiments on the KITTI dataset illustrate an improvement in AP of small objects up to 7.41%.