《计算机应用研究》|Application Research of Computers

基于R-SVM与SVDD的部位外观模型

Part appearance model based on R-SVM and SVDD

免费全文下载 (已被下载 次)  
获取PDF全文
作者 韩贵金,朱虹
机构 1.西安理工大学 自动化与信息工程学院,西安 710048;2.西安邮电大学 自动化学院,西安 710121
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2015)04-1272-04
DOI 10.3969/j.issn.1001-3695.2015.04.075
摘要 为克服现有基于HOG特征的部位外观模型未考虑不同细胞单元的不同作用以及不能准确表征相似度的缺陷,提出了一种基于递归支持向量机(R-SVM)和支持向量数据描述(SVDD)算法的人体部位外观模型。所提外观模型由两个分类器构成,利用R-SVM进行特征选择并建立的分类器用于判断图像某区域是否属于人体部位类,利用SVDD建立的相似度分类器用于计算属于人体部位类的图像区域与外观模型的相似度。将所提部位外观模型用于人体上半身姿态的估计,仿真实验结果显示其比现有部位外观模型的估计准确度更高,表明所提部位外观模型可以更准确地描述真实人体部位。
关键词 人体姿态估计;部位外观模型;递归支持向量机;支持向量数据描述;梯度方向直方图
基金项目 国际合作项目子项项目(2011DRF10480)
陕西省教育厅自然科学基金资助项目(2013JK0993)
本文URL http://www.arocmag.com/article/01-2015-04-075.html
英文标题 Part appearance model based on R-SVM and SVDD
作者英文名 HAN Gui-jin, ZHU Hong
机构英文名 1. Faculty of Automation & Information Engineering, Xi'an University of Technology, Xi'an 710048, China; 2. School of Automation, Xi'an University of Posts & Telecommunications, Xi'an 710121, China
英文摘要 For overcoming the defect that the existing part appearance models did not consider the different roles of different cells and could not represent the similarity accurately, this paper proposed an appearance model based on the recursive support vector machine(R-SVM) and support vector data description (SVDD) algorithm. The proposed appearance model consisted of two classifiers, the classifier built after feature selection by using R-SVM determined whether an image region belonged to the class of human part, the similarity classifier built by using SVDD calculated the similarity of an image region with the proposed appearance model. When used the proposed appearance model to human pose estimation, experiment results show that it can get higher estimation accuracy than the existing part appearance models, that indicate the proposed appearance models can represent real human part more accurately.
英文关键词 human pose estimation; part appearance model; recursive support vector machine; support vector data description; histogram of oriented gradient
参考文献 查看稿件参考文献
  [1] FISCHLER M, ELSCHLAGER R. The representation and matching of pictorial structures[J] . IEEE Trans on Computers, 1973, 22(1):67-92.
[2] FELZENSZWALB P, HUTTENLOCHER D. Pictorial structures for object recognition[J] . International Journal of Computer Vision, 2005, 61(1):55-79.
[3] THOMAS B M, HILTON A, KRUGER V, et al. Visual analysis of humans[M] . Berlin:Springer, 2011.
[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2005:886-893.
[5] SRINIVASAN P, SHI J. Bottom-up recognition and parsing of the human body[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2007:1-8.
[6] JOHNSON S, EVERINGHAM M. Combining discriminative appearance and segmentation cues for articulated human pose estimation[C] //Proc of the 12th International Conference on Computer Vision. Piscataway:IEEE Press, 2009:405-412.
[7] SAPP B, TOSHEV A, TASKAR B. Cascaded models for articulated pose estimation[C] //Proc of the 11th European Conference on Computer Vision. Berlin:Springer, 2010:406- 420.
[8] WANG Fang, LI Yi. Beyond physical connections:tree models in human pose estimation[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2013:596-603.
[9] YANG Yi, RAMANAN D. Articulated human detection with flexible mixtures of parts[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 2013, 35(12):2878-2890.
[10] FERRARI V, MARIN-JIMENEZ M, ZISSERMAN A. Progressive search space reduction for human pose estimation[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2008:1-8.
[11] ZHANG Xue-gong, LU Xin, SHI Qian, et al. Recursive SVM feature selection and sample classification for mass-spectrometry and microarray data[J] . BMC Bioinformatics, 2006, 7:197.
[12] 张学工. 模式识别[M] . 北京:清华大学出版社, 2010.
[13] DAVID M J, ROBERT P W. Support vector data description[J] . Machine Learning, 2004, 54(1):45-66.
[14] XIAO Yan-shan, LIU Bo, CAO Long-bing, et al. Multi-sphere support vector data description for outliers detection on multi distribution data[C] //Proc ofIEEE International Conference on Data Mining. Piscataway:IEEE Press, 2009:82-88.
[15] 薛贞霞, 刘三阳, 刘万里. 基于SVDD的渐进直推式支持向量机学习算法[J] . 模式识别与人工智能, 2008, 21(6):721-727.
[16] ANDRILUKA M, ROTH S, SCHIELE B. Pictorial structures revisited:people detection and articulated pose estimation[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2009:1014-1021.
[17] 韩贵金, 朱虹. 一种基于图结构模型的人体姿态估计算法[J] . 计算机工程与应用, 2013, 49(14):30-33.
[18] WU Ming-rui, YE Jie-ping. A small sphere and large margin approach for novelty detection using training data with outliers[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31(11):2088-2095.
收稿日期 2014/3/27
修回日期 2014/5/16
页码 1272-1275
中图分类号 TP391.41
文献标志码 A