KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection

Remote Sensing

Hua Wei¹  Changji Liu¹  Ming Zhu¹  Bo Wang¹  Jiarong Wang¹  Deyao Sun¹  Haitao Nie¹ 

[1] Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China;

关键词: 3D object detection;    multi-sensor fusion;    point cloud density enhancement;    attention mechanism;    autonomous driving;   

DOI  :  10.3390/rs12111895

来源: DOAJ

【 摘 要 】

In this paper, we propose a novel 3D object detector KDA3D, which achieves high-precision and robust classification, segmentation, and localization with the help of key-point densification and multi-attention guidance. The proposed end-to-end neural network architecture takes LIDAR point clouds as the main inputs that can be optionally complemented by RGB images. It consists of three parts: part-1 segments 3D foreground points and generates reliable proposals; part-2 (optional) enhances point cloud density and reconstructs the more compact full-point feature map; part-3 refines 3D bounding boxes and adds semantic segmentation as extra supervision. Our designed lightweight point-wise and channel-wise attention modules can adaptively strengthen the “skeleton” and “distinctiveness” point-features to help feature learning networks capture more representative or finer patterns. The proposed key-point densification component can generate pseudo-point clouds containing target information from monocular images through the distance preference strategy and K-means clustering so as to balance the density distribution and enrich sparse features. Extensive experiments on the KITTI and nuScenes 3D object detection benchmarks show that our KDA3D produces state-of-the-art results while running in near real-time with a low memory footprint.

【 授权许可】

Unknown