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

doi:10.1016/j.neucom.2021.06.046

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 智能机器人系统研究

	DVFENet: Dual-branch voxel feature extraction network for 3D object detection
	He, Yunqian 1; Xia, Guihua 1; Luo, Yongkang2 ; Su, Li 1; Zhang, Zhi 1; Li, Wanyi2 ; Wang, Peng2
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2021-10-12
卷号	459 页码:201-211
通讯作者	Xia, Guihua(xiaguihua@hrbeu.edu.cn)
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.
关键词	Point cloud 3D object detection Graph convolutional network Attention mechanism Decoupled RPN
DOI	10.1016/j.neucom.2021.06.046
收录类别	SCI
语种	英语
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]
项目资助者	Development Project of Ship Situational Intelligent Awareness System ; National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000711070700001
出版者	ELSEVIER
引用统计	被引频次：23[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46342
专题	多模态人工智能系统全国重点实验室_智能机器人系统研究
通讯作者	Xia, Guihua
作者单位	1.Harbin Engn Univ, Dept Automat, Harbin 150001, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, 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.