中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds

文献类型：期刊论文

作者Tian, Yonglin2,3; Huang, Lichao1; Yu, Hui6; Wu, Xiangbin5; Li, Xuesong3; Wang, Kunfeng4; Wang, Zilei2; Wang, Fei-Yue3
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2021-07-16
页码13
关键词Three-dimensional displays Feature extraction Convolution Proposals Kernel Laser radar Semantics Point clouds 3D detection dynamic network context features
ISSN号1524-9050
DOI10.1109/TITS.2021.3095719
通讯作者Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
英文摘要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.
资助项目Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China[62076020]
WOS研究方向Engineering ; Transportation
语种英语
WOS记录号WOS:000732917100001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/46839]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Wang, Fei-Yue
作者单位1.Horizon Robot, Beijing 100190, Peoples R China
2.Univ Sci & Technol China, Dept Automat, Hefei 230027, Anhui, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
4.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
5.Intel Labs, Beijing 100190, Peoples R China
6.Univ Portsmouth, Sch Creat Technol, Portsmouth PO1 2UP, Hants, England
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。