6D Object Pose Estimation in Cluttered Scenes from RGB Images

doi:10.1007/s11390-021-1311-2

CSpace

	6D Object Pose Estimation in Cluttered Scenes from RGB Images
	Yang, Xiao-Long 1,2; Jia, Xiao-Hong 1,2; Liang, Yuan 3; Fan, Lu-Bin 3
	2022-06-01
发表期刊	JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
ISSN	1000-9000
卷号	37 期号:3 页码:719-730
摘要	We propose a feature-fusion network for pose estimation directly from RGB images without any depth information in this study. First, we introduce a two-stream architecture consisting of segmentation and regression streams. The segmentation stream processes the spatial embedding features and obtains the corresponding image crop. These features are further coupled with the image crop in the fusion network. Second, we use an efficient perspective-n-point (E-PnP) algorithm in the regression stream to extract robust spatial features between 3D and 2D keypoints. Finally, we perform iterative refinement with an end-to-end mechanism to improve the estimation performance. We conduct experiments on two public datasets of YCB-Video and the challenging Occluded-LineMOD. The results show that our method outperforms state-of-the-art approaches in both the speed and the accuracy.
关键词	two-stream network 6D pose estimation fusion feature
DOI	10.1007/s11390-021-1311-2
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021YFB1715900] ; National Natural Science Foundation of China[12022117] ; National Natural Science Foundation of China[61802406] ; Beijing Natural Science Foundation[Z190004] ; Beijing Advanced Discipline Fund[115200S001] ; Alibaba Group through Alibaba Innovative Research Program
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS记录号	WOS:000812520400016
出版者	SCIENCE PRESS
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/61239
专题	中国科学院数学与系统科学研究院
通讯作者	Jia, Xiao-Hong
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Alibaba Grp, Alibaba DAMO Acad, Hangzhou 311121, Peoples R China
推荐引用方式 GB/T 7714	Yang, Xiao-Long,Jia, Xiao-Hong,Liang, Yuan,et al. 6D Object Pose Estimation in Cluttered Scenes from RGB Images[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2022,37(3):719-730.
APA	Yang, Xiao-Long,Jia, Xiao-Hong,Liang, Yuan,&Fan, Lu-Bin.(2022).6D Object Pose Estimation in Cluttered Scenes from RGB Images.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,37(3),719-730.
MLA	Yang, Xiao-Long,et al."6D Object Pose Estimation in Cluttered Scenes from RGB Images".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 37.3(2022):719-730.