DVFENet: Dual-branch voxel feature extraction network for 3D object detection

doi:10.1016/j.neucom.2021.06.046

	DVFENet: Dual-branch voxel feature extraction network for 3D object detection
	He, Yunqian 2; Xia, Guihua 2; Luo, Yongkang 1; Su, Li 2; Zhang, Zhi 2; Li, Wanyi 1; Wang, Peng 1
刊名	NEUROCOMPUTING
	2021-10-12
卷号	459 页码:201-211
关键词	Point cloud 3D object detection Graph convolutional network Attention mechanism Decoupled RPN
ISSN号	0925-2312
DOI	10.1016/j.neucom.2021.06.046
通讯作者	Xia, Guihua(xiaguihua@hrbeu.edu.cn)
英文摘要	3D object detection based on LiDAR point cloud has wide applications in autonomous driving and robotics. Recently, many approaches use voxelization representation in feature extraction and apply 3D convolution neural networks for 3D object detection. How to get expressive 3D voxelization represen-tation is important for the detection performance. Therefore, we propose a new 3D object detection framework (DVFENet) based on dual-branch voxel feature extraction, which can provide rich and com-plete 3D information. The first branch is a graph-attention-network-based voxel feature extraction, which applies an improved voxel graph attention feature extractor (VGAFE) on large-scale voxelization. This branch uses graph convolution networks with an attention mechanism to extract more local neigh-borhood and context information. The second branch is a 3D-sparse-convolution-based voxel feature extraction that captures finer geometric features based on small-scale voxelization. We also design a decoupled RPN module that can obtain task-specific features to reduce the task conflict. Experiments on the challenging KITTI 3D object detection benchmark and nuScenes detection task show that our method achieve good performance. At the same time, we conduct extensive experiments to verify the effectiveness of each component. (c) 2021 Elsevier B.V. All rights reserved.
资助项目	Development Project of Ship Situational Intelligent Awareness System[MC-201920-X01] ; National Natural Science Foundation of China[91748131] ; National Natural Science Foundation of China[U1613213] ; National Natural Science Foundation of China[61771471]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000711070700001
资助机构	Development Project of Ship Situational Intelligent Awareness System ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46341]
专题	智能机器人系统研究
通讯作者	Xia, Guihua
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Harbin Engn Univ, Dept Automat, Harbin 150001, Peoples R China
推荐引用方式 GB/T 7714	He, Yunqian,Xia, Guihua,Luo, Yongkang,et al. DVFENet: Dual-branch voxel feature extraction network for 3D object detection[J]. NEUROCOMPUTING,2021,459:201-211.
APA	He, Yunqian.,Xia, Guihua.,Luo, Yongkang.,Su, Li.,Zhang, Zhi.,...&Wang, Peng.(2021).DVFENet: Dual-branch voxel feature extraction network for 3D object detection.NEUROCOMPUTING,459,201-211.
MLA	He, Yunqian,et al."DVFENet: Dual-branch voxel feature extraction network for 3D object detection".NEUROCOMPUTING 459(2021):201-211.