PillarBAPI: Enhancing Pillar-Based 3D Object Detection through attentive Pseudo-Image Feature Extraction

Abstract

Three-dimensional (3D) object detection plays a pivotal role in autonomous driving and intelligent robots. However, current methods often struggle with false and missing detections, especially for small objects. To address these challenges, this paper introduces PillarBAPI, a high-performance 3D object detection network that improves pillar feature coding and enhances point cloud feature representation. PillarBAPI proposes an Attention-based Point and Pillar Feature Extraction (APFE) module to reduce information loss from maximum pooling and enable the model to focus on local and global features. Additionally, we introduce a Pseudo-Image Feature Extraction Network (PIFE) and a novel neck design, B-ASPP, to enhance pseudo-image feature extraction and promote multiscale feature fusion. Extensive experiments on the KITTI dataset demonstrate that Pillar BAPI achieves significant improvements in both 3D and Bird's Eye View (BEV) benchmarks, particularly for small target detection. The contributions of this work lie in the enhanced pillar feature coding, attentive feature extraction, and efficient multi-scale feature fusion, collectively contributing to improved 3D object detection performance. The code will be released at https://github.com/wangjie16138/PillarBAPI/.