DCGNN: a single-stage 3D object detection network based on density clustering and graph neural network
Shimin Xiong, Bin Li, Shiao Zhu
Abstract
Abstract Currently, single-stage point-based 3D object detection network remains underexplored. Many approaches worked on point cloud space without optimization and failed to capture the relationships among neighboring point sets. In this paper, we propose DCGNN, a novel single-stage 3D object detection network based on density clustering and graph neural networks. DCGNN utilizes density clustering ball query to partition the point cloud space and exploits local and global relationships by graph neural networks. Density clustering ball query optimizes the point cloud space partitioned by the original ball query approach to ensure the key point sets containing more detailed features of objects. Graph neural networks are very suitable for exploiting relationships among points and point sets. Additionally, as a single-stage 3D object detection network, DCGNN achieved fast inference speed. We evaluate our DCGNN on the KITTI dataset. Compared with the state-of-the-art approaches, the proposed DCGNN achieved better balance between detection performance and inference time.