期刊文献+

非规范视角步态识别研究 被引量:6

Research on nonstandard view gait identification
下载PDF
导出
摘要 大部分的步态识别算法都建立在能获得人体正侧面步态序列的基础上,而实际环境中人可能以任意角度接近摄像机。本文利用三维运动形成的速度场及运动场的关系,得到人在监控场景中行走的方位角,利用透视几何知识进行坐标转换,提出一种将任意视角下待识别人的行走序列矫正为规范视角下行走序列的算法,实验证明,将经过矫正的步态序列用于步态识别实验可明显提高识别率。 Most gait-recognition algorithms are based on getting side view of a person, but it is not realistic in most real-life scenarios. It is possible to synthesize a side view from any other arbitrary view using the perspective projection model and optical flow based structure from motion equations. Experiment show that using this method we can improve the identification rate effectively.
出处 《仪器仪表学报》 EI CAS CSCD 北大核心 2008年第10期2058-2061,共4页 Chinese Journal of Scientific Instrument
基金 国家自然科学基金(60474035) 国家教育部博士点基金(20060359004)资助项目
关键词 步态识别 隐马尔可夫模型 透视几何 运动场 gait identification HMM perspective projection structure from motion
  • 相关文献

参考文献14

  • 1FAUGERAS O D. Three-dimensional computer vision:a geometric viewpoint [ M ]. MIT Press, 1993.
  • 2HARTLEY R I, ZISSERMAN A. Multiple view geometry in computer vision[ M]. Cambridge University Press, 2000.
  • 3BOBICK A F, JOHNSON A. Gait recognition using static activity-specific parameters[ C ]. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2001.
  • 4BOBICK J. A multi-view method for gait recognition using static body parameters [ A]. Proceedings of 3rd International Conference on Audio and Video Based Biometric Person Authentication[ C ]. Halmstad, Sweden, 2001:301-311.
  • 5彭彰,吴晓娟,杨军.基于肢体长度参数的多视角步态识别算法[J].自动化学报,2007,33(2):210-213. 被引量:10
  • 6SHAKHNAROVICH G, LEE L, DARRELL T. Integrated face and gait recognition from multiple views [ C ]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2001.
  • 7NALWA V. A guided tour of computer vision[ M]. Addison-Wesley, 1993.
  • 8TSAI R T. A versatile camera calibration technique for high accuracy 3D machine vision metrology using off-the shelf TV camera and lenses[ J]. IEEE Journal of Robotics and Automation, 1987, RA 3 (4) :323-344.
  • 9邹凤娇,苏显渝,李美菊.基于共面点的摄像机线性标定法[J].光电工程,2005,32(4):70-74. 被引量:39
  • 10PHILLIPS P J, SARKAR S, ROBLEDO, et al. The gait identification challenge problem:Datasets and baseline algorithm [ C ]. Proc of the International Conference on Pattern Recognition, 2002.

二级参考文献37

  • 1张健新,段发阶,叶声华.双目传感器结构优化设计[J].光电工程,1996,23(3):12-17. 被引量:9
  • 2章毓晋.图像分割[M].北京:科学出版社,2001.34.
  • 3Roger Y.TSAI.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses [J].IEEE Journal of Robotics and Automation,1987,3(4):323-334.
  • 4Zheng-you ZHANG.A flexible new technique for camera calibration [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
  • 5S.M.SMITH,J.M.BRADY.SUSAN-A new approach to low level image processing [J].International Journal of Computer Vision,1997,23(1):45-78.
  • 6马颂德 张正友.计算机视觉[M].北京:科学出版社,1998.72-80.
  • 7Wang L, Hu W, Tan T. Recent developments in human motion analysis. Pattern Recognition,2003,36(3):585~601
  • 8Phillips J, Moon H, Rizvi S, Rause P. The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(10): 1090~1104
  • 9Jain A, Bolle R, Pankanti S. Biometrics: Personal Identification in Networked Society. Boston:Kluwer Academic Publishers, 1999
  • 10Nixon M, Carter J, Cunado D, Huang P, Stevenage S. Automatic gait recognition. In: Proceedings of BIOMETRICS Personal Identification in Networked Society, 1999. 231~249

共引文献202

同被引文献48

引证文献6

二级引证文献31

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部