Slow Feature Analysis for Human Action Recognition

CASIA OpenIR > 智能感知与计算研究中心

	Slow Feature Analysis for Human Action Recognition
	Zhang, Zhang1 ; Tao, Dacheng 2
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2012-03-01
卷号	34 期号:3 页码:436-450
文章类型	Article
摘要	Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal [1]. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition. Experimental results suggest that the SFA-based approach 1) is able to extract useful motion patterns and improves the recognition performance, 2) requires less intermediate processing steps but achieves comparable or even better performance, and 3) has good potential to recognize complex multiperson activities.
关键词	Human Action Recognition Slow Feature Analysis
WOS标题词	Science & Technology ; Technology
关键词[WOS]	FACE RECOGNITION ; POINTS
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000299381600002
引用统计	被引频次：246[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/173211/8003
专题	智能感知与计算研究中心
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 2.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zhang, Zhang,Tao, Dacheng. Slow Feature Analysis for Human Action Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2012,34(3):436-450.
APA	Zhang, Zhang,&Tao, Dacheng.(2012).Slow Feature Analysis for Human Action Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,34(3),436-450.
MLA	Zhang, Zhang,et al."Slow Feature Analysis for Human Action Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 34.3(2012):436-450.