RPEA: A Residual Path Network with Efficient Attention for 3D pedestrian detection from LiDAR point clouds

Abstract

Efficiently detecting pedestrians from 3D point cloud data is a significantly challenging perception task in numerous robotic and autonomous driving applications, primarily because of the sparsity of point cloud data representing pedestrian objects and the significant deformations in pedestrian body poses. To address these challenges, we present a Residual Path network with Efficient Attention (RPEA), an end-to-end trainable single-stage 3D pedestrian detection network. We first introduce the Residual Path (ResPath) architecture, which incorporates multiple residual blocks to retain the spatial information lost during downsampling and combines features of different resolution scales. To suppress noise in point clouds while generalizing various pedestrian representations, we propose an efficient Channel Attention module with Average and Maximum pooling strategies (CAAM). Experimental results demonstrate that our RPEA ranks first on the JRDB 3D object detection leaderboard among all solutions, while significantly surpassing the ranks second by up to 5.6% average precision. Additionally, our RPEA achieves real-time pedestrian detection at 39 frame-per-second (fps). Since our method has higher accuracy and faster inference, it can be deployed more effectively in vehicles and mobile robots. The code is publicly available at https://github.com/jinzhengguang/RPEA.