Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds

doi:10.1109/TITS.2021.3095719

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds
	Tian, Yonglin1,2 ; Huang, Lichao 3; Yu, Hui 4; Wu, Xiangbin 5; Li, Xuesong2 ; Wang, Kunfeng6 ; Wang, Zilei 1; Wang, Fei-Yue2
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2021-07-16
页码	13
通讯作者	Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
摘要	Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context. Point-level contexts are generated from original point clouds to enlarge the effective receptive filed. They are extracted around the voxelized pillars based on our extended voxelization method and processed with the context encoder in parallel with the pillar features. With a large perception range, we are able to capture the variance of features for potential objects and generate attentive spatial guidance to help adjust the strengths for different regions. In the region proposal network, considering the limited representation ability of traditional convolution where same kernels are shared among different samples and positions, we propose a decomposable dynamic convolutional layer to adapt to the variance of input features by learning from the local semantic context. It adaptively generates the position-dependent coefficients for multiple fixed kernels and combines them to convolve with local features. Based on our dynamic convolution, we design a dual-path convolution block to further improve the representation ability. We conduct experiments on KITTI dataset and the proposed CADNet has achieved superior performance of 3D detection outperforming SECOND and PointPillars by a large margin at the speed of 30 FPS.
关键词	Three-dimensional displays Feature extraction Convolution Proposals Kernel Laser radar Semantics Point clouds 3D detection dynamic network context features
DOI	10.1109/TITS.2021.3095719
收录类别	SCI
语种	英语
资助项目	Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China[62076020]
项目资助者	Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000732917100001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	人工智能+交通
引用统计	被引频次：11[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/173211/46840
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Wang, Fei-Yue
作者单位	1.Univ Sci & Technol China, Dept Automat, Hefei 230027, Anhui, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Horizon Robot, Beijing 100190, Peoples R China 4.Univ Portsmouth, Sch Creat Technol, Portsmouth PO1 2UP, Hants, England 5.Intel Labs, Beijing 100190, Peoples R China 6.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Tian, Yonglin,Huang, Lichao,Yu, Hui,et al. Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021:13.
APA	Tian, Yonglin.,Huang, Lichao.,Yu, Hui.,Wu, Xiangbin.,Li, Xuesong.,...&Wang, Fei-Yue.(2021).Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,13.
MLA	Tian, Yonglin,et al."Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021):13.