Action recognition using linear dynamic systems

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Action recognition using linear dynamic systems; Action recognition using linear dynamic systems
	Wang, Haoran 1,2; Yuan, Chunfeng2 ; Luo, Guan2 ; Hu, Weiming2 ; Sun, Changyin 1
发表期刊	PATTERN RECOGNITION ; PATTERN RECOGNITION
	2013-06-01 ; 2013-06-01
卷号	46 期号:6 页码:1710-1718
文章类型	Article ; Article
摘要	In this paper, we propose a novel approach based on Linear Dynamic Systems (LDSs) for action recognition. Our main contributions are two-fold. First, we introduce LDSs to action recognition. LDSs describe the dynamic texture which exhibits certain stationarity properties in time. They are adopted to model the spatiotemporal patches which are extracted from the video sequence, because the spatiotemporal patch is more analogous to a linear time invariant system than the video sequence. Notably, LDSs do not live in the Euclidean space. So we adopt the kernel principal angle to measure the similarity between LDSs, and then the multiclass spectral clustering is used to generate the codebook for the bag of features representation. Second, we propose a supervised codebook pruning method to preserve the discriminative visual words and suppress the noise in each action class. The visual words which maximize the inter-class distance and minimize the intra-class distance are selected for classification. Our approach yields the state-of-the-art performance on three benchmark datasets. Especially, the experiments on the challenging UCF Sports and Feature Films datasets demonstrate the effectiveness of the proposed approach in realistic complex scenarios. (C) 2012 Elsevier Ltd. All rights reserved.; In this paper, we propose a novel approach based on Linear Dynamic Systems (LDSs) for action recognition. Our main contributions are two-fold. First, we introduce LDSs to action recognition. LDSs describe the dynamic texture which exhibits certain stationarity properties in time. They are adopted to model the spatiotemporal patches which are extracted from the video sequence, because the spatiotemporal patch is more analogous to a linear time invariant system than the video sequence. Notably, LDSs do not live in the Euclidean space. So we adopt the kernel principal angle to measure the similarity between LDSs, and then the multiclass spectral clustering is used to generate the codebook for the bag of features representation. Second, we propose a supervised codebook pruning method to preserve the discriminative visual words and suppress the noise in each action class. The visual words which maximize the inter-class distance and minimize the intra-class distance are selected for classification. Our approach yields the state-of-the-art performance on three benchmark datasets. Especially, the experiments on the challenging UCF Sports and Feature Films datasets demonstrate the effectiveness of the proposed approach in realistic complex scenarios. (C) 2012 Elsevier Ltd. All rights reserved.
关键词	Linear Dynamic System Linear Dynamic System Kernel Principal Angle Kernel Principal Angle Multiclass Spectral Clustering Multiclass Spectral Clustering Supervised Codebook Pruning Supervised Codebook Pruning Action Recognition Action Recognition
WOS标题词	Science & Technology ; Science & Technology ; Technology ; Technology
关键词[WOS]	IMAGE SEGMENTATION ; IMAGE SEGMENTATION ; TEXTURE ; TEXTURE ; CONTOUR ; CONTOUR ; SHAPE ; SHAPE
收录类别	SCI ; SCI
语种	英语 ; 英语
WOS研究方向	Computer Science ; Computer Science ; Engineering ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Engineering, Electrical & Electronic
WOS记录号	WOS:000315369900016 ; WOS:000315369900016
引用统计	被引频次：10[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/173211/3280
专题	多模态人工智能系统全国重点实验室_视频内容安全
作者单位	1.Southeast Univ, Sch Automat, Nanjing, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
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	Wang, Haoran,Yuan, Chunfeng,Luo, Guan,et al. Action recognition using linear dynamic systems, Action recognition using linear dynamic systems[J]. PATTERN RECOGNITION, PATTERN RECOGNITION,2013, 2013,46, 46(6):1710-1718, 1710-1718.
APA	Wang, Haoran,Yuan, Chunfeng,Luo, Guan,Hu, Weiming,&Sun, Changyin.(2013).Action recognition using linear dynamic systems.PATTERN RECOGNITION,46(6),1710-1718.
MLA	Wang, Haoran,et al."Action recognition using linear dynamic systems".PATTERN RECOGNITION 46.6(2013):1710-1718.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
1-s2.0-S003132031200（648KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载