Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising

doi:10.1109/TCYB.2014.2381659

OPT OpenIR > 光谱成像技术研究室

	Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising
	Feng, Yinfu 1; Ji, Mingming 1; Xiao, Jun 1; Yang, Xiaosong 2; Zhang, Jian J.2; Zhuang, Yueting 1; Li, Xuelong3
	2015-12-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
卷号	45 期号:12 页码:2693-2706
摘要	Motion capture is an important technique with a wide range of applications in areas such as computer vision, computer animation, film production, and medical rehabilitation. Even with the professional motion capture systems, the acquired raw data mostly contain inevitable noises and outliers. To denoise the data, numerous methods have been developed, while this problem still remains a challenge due to the high complexity of human motion and the diversity of real-life situations. In this paper, we propose a data-driven-based robust human motion denoising approach by mining the spatial-temporal patterns and the structural sparsity embedded in motion data. We first replace the regularly used entire pose model with a much fine-grained partlet model as feature representation to exploit the abundant local body part posture and movement similarities. Then, a robust dictionary learning algorithm is proposed to learn multiple compact and representative motion dictionaries from the training data in parallel. Finally, we reformulate the human motion denoising problem as a robust structured sparse coding problem in which both the noise distribution information and the temporal smoothness property of human motion have been jointly taken into account. Compared with several state-of-the-art motion denoising methods on both the synthetic and real noisy motion data, our method consistently yields better performance than its counterparts. The outputs of our approach are much more stable than that of the others. In addition, it is much easier to setup the training dataset of our method than that of the other data-driven-based methods.
文章类型	Article
关键词	Human Motion Denoising Microsoft Kinect l(2 Motion Capture Data p)-norm Robust Dictionary Learning Robust Structured Sparse Coding
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2014.2381659
收录类别	SCI
关键词[WOS]	ACTION RECOGNITION ; CAPTURE ; REPRESENTATION ; IMAGES ; ANIMATION ; WAVELETS ; PURSUIT ; NOISE
语种	英语
WOS研究方向	Computer Science
项目资助者	National Key Basic Research Program of China(2012CB316400) ; National High Technology Research and Development Program(2012AA011502) ; Zhejiang Provincial Natural Science Foundation of China(LY13F020001) ; Fundamental Research Funds for the Central Universities(2014FZA5013) ; Zhejiang Province Public Technology Applied Research Projects(2014C33090) ; Sino-U.K. Higher Education Research Partnership for Ph.D. student's project - Department of Business, Innovation, and Skills of the British Government ; Ministry of Education of China
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000365320300006
引用统计	被引频次：33[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/27547
专题	光谱成像技术研究室
作者单位	1.Zhejiang Univ, Coll Comp Sci, Hangzhou 310027, Zhejiang, Peoples R China 2.Bournemouth Univ, Natl Ctr Comp Animat, Poole BH12 5BB, Dorset, England 3.Chinese Acad Sci, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Feng, Yinfu,Ji, Mingming,Xiao, Jun,et al. Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising[J]. IEEE TRANSACTIONS ON CYBERNETICS,2015,45(12):2693-2706.
APA	Feng, Yinfu.,Ji, Mingming.,Xiao, Jun.,Yang, Xiaosong.,Zhang, Jian J..,...&Li, Xuelong.(2015).Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising.IEEE TRANSACTIONS ON CYBERNETICS,45(12),2693-2706.
MLA	Feng, Yinfu,et al."Mining Spatial-Temporal Patterns and Structural Sparsity for Human Motion Data Denoising".IEEE TRANSACTIONS ON CYBERNETICS 45.12(2015):2693-2706.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Mining Spatial-Tempo（2074KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文