Action recognition by spatio-temporal oriented energies

doi:10.1016/j.ins.2014.05.021

OPT OpenIR > 光谱成像技术研究室

	Action recognition by spatio-temporal oriented energies
	Zhen, Xiantong 1,2; Shao, Ling 1,2; Li, Xuelong3
作者部门	光学影像学习与分析中心
	2014-10-10
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
卷号	281 页码:295-309
摘要	In this paper, we present a unified representation based on the spatio-temporal steerable pyramid (STSP) for the holistic representation of human actions. A video sequence is viewed as a spatio-temporal volume preserving all the appearance and motion information of an action in it. By decomposing the spatio-temporal volumes into band-passed sub-volumes, the spatio-temporal Laplacian pyramid provides an effective technique for multi-scale analysis of video sequences, and spatio-temporal patterns with different scales could be well localized and captured. To efficiently explore the underlying local spatio-temporal orientation structures at multiple scales, a bank of three-dimensional separable steerable filters are conducted on each of the sub-volume from the Laplacian pyramid. The outputs of the quad-rature pair of steerable filters are squared and summed to yield a more robust oriented energy representation. To be further invariant and compact, a spatio-temporal max pooling operation is performed between responses of the filtering at adjacent scales and over spatio-temporal neighbourhoods. In order to capture the appearance, local geometric structure and motion of an action, we apply the STSP on the intensity, 3D gradients and optical flow of video sequences, yielding a unified holistic representation of human actions.
文章类型	Article
关键词	Action Recognition Steerable Filters Spatio-temporal Oriented Energies Spatio-temporal Laplacian Pyramid
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.ins.2014.05.021
收录类别	SCI ; EI
关键词[WOS]	SCENE CLASSIFICATION ; VISUAL-ATTENTION ; REPRESENTATION ; MOTION ; MODELS
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000340315600019
引用统计	被引频次：44[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/181661/22386
专题	光谱成像技术研究室
作者单位	1.Nanjing Univ Informat Sci & Technol, Coll Elect & Informat Engn, Nanjing 210044, Jiangsu, Peoples R China 2.Univ Sheffield, Dept Elect & Elect Engn, Sheffield S1 3JD, S Yorkshire, England 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Zhen, Xiantong,Shao, Ling,Li, Xuelong. Action recognition by spatio-temporal oriented energies[J]. INFORMATION SCIENCES,2014,281:295-309.
APA	Zhen, Xiantong,Shao, Ling,&Li, Xuelong.(2014).Action recognition by spatio-temporal oriented energies.INFORMATION SCIENCES,281,295-309.
MLA	Zhen, Xiantong,et al."Action recognition by spatio-temporal oriented energies".INFORMATION SCIENCES 281(2014):295-309.

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
Action recognition b（2053KB）	期刊论文	出版稿	限制开放	CC BY	请求全文