Gait recognition using kernel independent component analysis with hypo-periodicity

doi:10.3778/j.issn.1002-8331.2010.34.052

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (34): 171-173.DOI: 10.3778/j.issn.1002-8331.2010.34.052

• 图形、图像、模式识别 • Previous Articles Next Articles

Gait recognition using kernel independent component analysis with hypo-periodicity

WEI Su-yuan^1，2，NING Chao²，GAO You-xing¹

1.Research Insititute of Computer Peripheral，Xidian University，Xi’an 710071，China
2.Second Artillery Engineering College，Xi’an 710025，China

Received:2009-04-07 Revised:2009-07-20 Online:2010-12-01 Published:2010-12-01
Contact: WEI Su-yuan

应用核独立成分分析进行弱周期性步态识别研究

韦素媛^1，2，宁超²，高有行¹

1.西安电子科技大学外部设备研究所，西安 710071
2.第二炮兵工程学院，西安 710025

通讯作者: 韦素媛

Abstract

Abstract: A novel gait representation based on the Spatio-Temporal Energy（STE） image and the Kernel Independent Component Analysis（KICA） is proposed.It uses the nonlinear features and high-dimension statistical information of gait，and deals with the problem of time-dependence and the gait cycle extraction.The recognition rate is around 93.9% in SOTON dataset with 10 persons gait sequences.The results demonstrate that the method has the encouraging performance，as well as the merit of low space and time requirement.

摘要： 提出一种基于时空能量图和核独立成分分析的步态特征表达和步态识别方法，利用步态序列图像的非线性特征和高维统计信息，并消除识别算法对时间配准和步态周期定位的依赖，时空能量图集成了步行运动信息中时间与空间变化的特点，并极大地减少了特征的数据量。针对10人值班的涉密场所进行步态识别正确率达到93.9%。实验结果表明该算法具有较好的识别性能和相当低的空间需求和计算量。

CLC Number:

TP391.41

WEI Su-yuan^1，2，NING Chao²，GAO You-xing¹. Gait recognition using kernel independent component analysis with hypo-periodicity[J]. Computer Engineering and Applications, 2010, 46(34): 171-173.

韦素媛^1，2，宁超²，高有行¹. 应用核独立成分分析进行弱周期性步态识别研究[J]. 计算机工程与应用, 2010, 46(34): 171-173.

[1]	LIU Guangshuai，LI Bailin，HE Chaoming. Patch-graph sparse optimization methods based on piecewise smooth surfaces reconstruction [J]. Computer Engineering and Applications, 2011, 47(4): 22-25.
[2]	ZHANG Cong，GUI Zhiguo. Non-linear image sharpening approach based on noise estimation [J]. Computer Engineering and Applications, 2011, 47(4): 154-156.
[3]	SUN Lisheng，ZHENG Jianjing，CHEN Jianjun，DAI Meihuang，LIANG Yi. Two-dimensional adaptive advancing front mesh generation [J]. Computer Engineering and Applications, 2011, 47(3): 146-148.
[4]	ZHANG Ying，LI Yanjun，ZHANG Ke，WANG Hongmei. Fusion of infrared and visible images based on nonsubsampled Contourlet transform [J]. Computer Engineering and Applications, 2011, 47(3): 196-198.
[5]	LIU Weifeng，LI Shujuan，WANG Yanjiang. Facial expression analysis using LBP features [J]. Computer Engineering and Applications, 2011, 47(2): 149-152.
[6]	DUAN Jianwei，PENG Guohua，HU Meigui. Binary subdivision scheme with three parameters for surface design [J]. Computer Engineering and Applications, 2011, 47(2): 194-196.
[7]	TANG Min. Complete stability analysis and primary application of standard cellular neural networks [J]. Computer Engineering and Applications, 2011, 47(2): 173-175.
[8]	HU Xiaodong¹，LUO Jiancheng¹，WU Wei¹，CHENG Xi¹，SHEN Zhanfeng¹，JIA Yinfang². Automatic recognition method of chalk handwritten numerals [J]. Computer Engineering and Applications, 2011, 47(2): 182-184.
[9]	CHEN Zhanzhan，TANG Jin，LUO Bin，KONG Min. Skeleton tree matching based on optimal subsequence bijection [J]. Computer Engineering and Applications, 2011, 47(1): 162-165.
[10]	GUO Hualei^1，2，MA Miao¹. Image segmentation based on improved Fuzzy C-Means clustering [J]. Computer Engineering and Applications, 2011, 47(1): 176-178.
[11]	YANG Maolong^1，2，WANG Yuanfang³，SUN Quansen²，XIA Deshen². Improved partial least squares and feature extraction [J]. Computer Engineering and Applications, 2011, 47(1): 179-181.
[12]	YUAN Kui，XIAO Han，HE Wen-hao. Survey on machine vision systems based on FPGA [J]. Computer Engineering and Applications, 2010, 46(36): 1-6.
[13]	YANG Fu-yan，ZHOU Ming-quan，DENG Qing-qiong. Scribble-based interactive mesh segmentation [J]. Computer Engineering and Applications, 2010, 46(36): 175-177.
[14]	ZHAO Jun，XIAO Bing. Quadric reconstruction and classification based on boundary [J]. Computer Engineering and Applications, 2010, 46(35): 199-201.
[15]	WU Gang. Research on analysis of information similarity based on implicit polynomial curves [J]. Computer Engineering and Applications, 2010, 46(35): 228-230.

Gait recognition using kernel independent component analysis with hypo-periodicity

应用核独立成分分析进行弱周期性步态识别研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics