期刊文献+

基于HOG的人体检测方法的改进 被引量:4

下载PDF
导出
摘要 从图像中检测出人体是计算机视觉应用中的关键步骤。Dalal等人提出的基于方向梯度直方图(Histogramsof Oriented Gradient,HOG)的人体检测是一种性能优异的单一窗口人体检测方法,将其用于人体检测性能优于Haar,PCA-SIFT和Shape context等方法,但以HOG作为人体特征的人体检测存在向量维数较大、检测时间较长的问题。为提高基于HOG的人体检测的速度,提出了通过一个由简到繁的级联线性SVM分类器将级联拒绝的机制与基于感兴趣区的HOG特征计算相结合的人体检测方法,既能保持Dalal算法检测的准确性,又可大幅度地提高检测速度。
作者 周金芝 王娟
出处 《软件导刊》 2011年第4期76-78,共3页 Software Guide
  • 相关文献

参考文献3

二级参考文献20

  • 1潘锋,王宣银.基于支持向量机的复杂背景下的人体检测[J].中国图象图形学报(A辑),2005,10(2):181-186. 被引量:16
  • 2Schauland S, Park S B, Zhang Yan. Vision-based Pedestrian Detection Improvement and Verification of Feature Extraction Methods and SVM-based Classification[C]//Proc. of IEEE Intelligent Transportation Systems Conference. [S. l.]: IEEE Press, 2006: 97-102. 被引量:1
  • 3Dalai N. Finding People in Images and Videos[D]. Grenoble, France: The French National Institute for Research in Computer Science and Control, 2006. 被引量:1
  • 4Mohan A, Papageorgiou C, Poggio T. Example-Based object detection in images by components [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(4) :349 -361. 被引量:1
  • 5Mikolajczyk K,Schmid C,Zisserman A. Human detection based on a probabilistic assembly of robust part detectors [ A ]. In:Proceedings of 8tb European Conference on Computer Vision [ C ]. Prague, Czech, 2004,69 - 82. 被引量:1
  • 6Ronfard R, Schmid C, Triggs B. Learning to parse pictures of people [ A ]. In:Proceedings of 6th European Conference on Computer Vision [ C ]. Copenhagen, Denmark ,2002:700 - 714. 被引量:1
  • 7Felzenszwalb P F, Huttenlocher D P. Pictorial stuctures for object recognition [ J]. International Journal of Computer Vision, 2005, 61(1) :55 -79. 被引量:1
  • 8Ioffe S, Forsyth D A. Probabilistic methods for finding people [ J]. International Journal of Computer Vision ,2001,43( 1 ) :45 -68. 被引量:1
  • 9Leibe B,Leonardis A, Schiele B. Pedstrain detection in crowed scenes [ A]. In: Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition [ C ]. San Diego, CA, USA, 2005: 878 - 885. 被引量:1
  • 10Papageorgiou C, Poggio T. A trainable system for object detection [ J ]. International Journal of Computer Vision, 2000, 38 ( 1 ) : 15 -33. 被引量:1

共引文献35

同被引文献31

  • 1胡仕玲,顾爽,陈启军.基于HOG的物体分类方法[J].华中科技大学学报(自然科学版),2011,39(S2):124-126. 被引量:7
  • 2方辉,王倩.支持向量机的算法研究[J].长春师范学院学报(自然科学版),2007,26(3):90-91. 被引量:13
  • 3Wang J, Cohen M F. Image and video matting; A survey [ J ]. Founfa- tions and Trends (R) in Computer Graphics and vision,2007,3 ( 2 ) : 97 - 175. 被引量:1
  • 4Wang O, Finger J, Yang Q, et al. Automatic natural video matting with depth [ C ]//Proc of Pacific Graphics. Hawaii, USA : IEEE Press,2007 : 469 - 472. 被引量:1
  • 5Gao S H,Tsang I W,Liang T,et al. Local features are not lonely-Lapla-cian sparse coding for image classification [ C ]//Proc. CVPR. 2009 : 1794 - 1801. 被引量:1
  • 6Lowe D G. Distinctive image features from scale invariant key points [J]. IJCV,2004,60(2) :91 - 110. 被引量:1
  • 7Belongie S, Malik J,Puzicha J. Matching shapes [ C ]//The 8th ICCV, Vancouver, Canada,2001 : 454 - 461. 被引量:1
  • 8Dalai N ,Triggs B. Histograms of oriented gradients for human detection [ C]//San Diego. CA. United states: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition ,2005 : 886 - 893. 被引量:1
  • 9Felzenszwalb P, Huttenlocher D. Efficient matching of pictorial structures [ C ]//CVPR,2000:66 - 73. 被引量:1
  • 10Ya Chang, Changbo Hu, Rogerio Feris. Manifold based analysis of facial expression [ C ]//Image and Vision Computing, 2006:605 - 614. 被引量:1

引证文献4

二级引证文献6

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