Prior Distribution and Perception Radius Are Important: Learning 3-D Object Detector for Autonomous Driving
Ziming Tao, Jianxu Mao, Weixing Peng, Yaonan Wang, Junfei Yi, Hui Zhang · IEEE Transactions on Instrumentation and Measurement · 2025
This article proposes an efficient 3D object detection algorithm for LiDAR point clouds in the field of autonomous driving. Currently, despite significant performance improvements in 3D LiDAR object detection methods, there are still problems that have impact on 3D detection accuracy. Typically, since the sampling process and grouping process introduced background points, the final regression step in detection task would be greatly affected. To address this problem, a method named PR-SSD is proposed to retain more important foreground points during the training pipeline, improving detection accuracy. Specifically, the proposed approach utilizes prior information to guide semantic sampling, referred to as Prior Distributed Semantic Sampling (PDSS). This mechanism encourages the network to prioritize foreground targets in regression. Additionally, a module named Radius-aware Attention Multi-scale Grouping (RAMSG) is designed to dynamically re-assign grouping weights for multi-scale features. In other words, the network has adaptive detection capabilities for targets of different scales. Furthermore, PR-SSD is a single-stage detector which can be trained end-to-end. Finally, extensive experiments and evaluations on large-scale benchmarks KITTI demonstrate that our proposed method significantly enhanced 3D object detector. In KITTI test set, PR-SSD achieves 89.69%, 45.08%, and 80.01% detection performance for car, pedestrian and cyclist.