全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

身份识别中步态特征的提取

Keywords: 步态识别,骨骼化模型,光流场,主元分析

Full-Text   Cite this paper   Add to My Lib

Abstract:

阐述了2种简单有效的基于步态的身份识别方法——基于模型的方法和非基于模型的方法.基于模型的方法利用人体的骨骼化模型,首先对输入的图像序列自动进行背景初始化;然后分割图像中运动人体的侧面影像,并进一步细化为人体的骨骼化模型;接着从模型中提取人体的静态参数以及动态参数作为特征.非基于模型的方法计算图像间的光流场,从光流场中进一步提取可识别特征.将2种方法应用于室内拍摄的视频,实验结果表明,通过提取可靠的步态特征,降低了数据处理的代价,而且得到了较好的识别性能.

References

[1]  JOHANSSON G. Visual perception of biological motion and a model for its analysis[J]. Perception and Psychophysics, 1973, 14(2): 201-211.
[2]  CUNADO D, NIXON M S, CARTER J N. Using gait as a biometric, via phase-weighted magnitude spectra[A]. Lecture Notes in Computer Science Proc[C]. University of Southampton, Southampton UK. 1997.
[3]  王亮,胡卫明,谭铁牛.基于步态的身份识别[J].计算机学报,2003(3):353-360. WANG Liang, HU Wei-ming, TAN Tie-niu. Identification based on gait [J]. Chinese Journal of Computers, 2003(3): 353-360. (in Chinese)
[4]  耿超,苏开娜,段娟.人群分裂后的人体运动跟踪[J].计算机工程,2005(8):249-252. GENG Chao, SU Kai-na, DUANG Juan. Human motion detection and tracking[J]. Computer Engineer, 2005(8): 249-252. (in Chinese)
[5]  吴立德.计算机视觉[M].上海:复旦大学出版社,1993.180-205. WU Li-de. Computer Vision[M]. Shanghai: Publishing Company of Fudan University, 1993. 180-205. (in Chinese)
[6]  吴新根,罗立民.一种改进的光流场计算方法[J].电子学报,2000,28(1):130-131. WU Xin-gen, LUO Li-min. An improve method of optical flow estimation[J] . Chinese Journal of Electronics, 2000, 28(1): 130-131. (in Chinese)
[7]  YOO Jang-hee, NIXON M S, HARRIS C J. Extracting Human Gait Signatures by Body Segment Properties[A]. Proceed ings of Proc IEEE Southwest Symposium on Image Analysis and Interpretation[C]. University of Southampton, Southampton UK. 2002.
[8]  LITTLE J, BOYD J E. Recognizing people by their gait: The shape of motion[J]. Journal of Computer Vision Research, 1998, 1(2): 2-32.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133