期刊文献+

判别式BoW分析结合自适应码本学习的人体动作识别 被引量:3

Application of discriminant BoW analysis combined with adaptive codebook learning in human recognition
下载PDF
导出
摘要 针对一般聚类获得的码本缺乏判别性表示导致不能有效进行人体动作识别的问题,提出了一种新的自适应码本学习方法,该方法将判别式词袋(bag of words,Bo W)动作表示和自适应码本学习结合,增强了码本的表示能力和特征的判别性。为了有效求解非凸目标函数,提出基于轮换优化迭代方法,即固定码本更新判别矩阵,然后判别矩阵更新固定码本,直至满足终止迭代条件,该方法为自适应码本学习提供了技术支持。仿真实验采用KTH、Hollywood2、芭蕾、i3Dpost数据库进行判别比较,识别率比现有典型方法平均提高了4%左右,学习到的码本在特征空间中具有良好的判别性能。相比于基于光流、方向梯度直方图(histograms of oriented gradients,HOG)等方法,计算复杂度更低,实用性更好。 As the problem of ineffective human action recognition caused by lack of judgment representation of codebook obtained by general clustering,this paper proposed a new adaptive codebook learning method,combined discriminant bag of words with adaptive codebook learning,which had enhanced the ability to represent features of codebook discriminant. In order to effectively solve the non-convex objective function,it proposed iteration of rotational optimization,that was the fixed codebook updated the judgment matrix,and then the judgment matrix updated the fixed codebook until it met the conditions for termination of the iteration. This method provided technical support for the adaptive codebook learning. In the simulation experiments,it tested five data sets KTH,Hollywood2,ballet,i3 Dpost and facial expressions. The experimental result is about 4% recognition rate averagely higher than the existing typical methods. The learned codebook has good discrimination performance in the feature space. Compared with optical flow method,the method based on the histograms of oriented gradients( HOG) and other methods,the proposed method has lower computational complexity and better usability.
出处 《计算机应用研究》 CSCD 北大核心 2016年第5期1576-1580,共5页 Application Research of Computers
基金 国家自然科学基金资助项目(61173036) 湖南省教育厅科学研究项目(12C1174)
关键词 人体动作识别 判别式词袋 自适应 码本学习 轮换优化迭代 human action recognition discriminant BoW adaptive codebook learning iteration of rotational optimization
  • 相关文献

参考文献17

  • 1李瑞峰,王亮亮,王珂.人体动作行为识别研究综述[J].模式识别与人工智能,2014,27(1):35-48. 被引量:96
  • 2郭利,姬晓飞,李平,曹江涛.基于混合特征的人体动作识别改进算法[J].计算机应用研究,2013,30(2):601-604. 被引量:14
  • 3Burghouts G J, Schutte K. Spatio-temporal layout of human actions for improved bag-of-words action detection [ J ]. Pattern Recognition Letters,2013,34( 15 ) :1861-1869. 被引量:1
  • 4Yang .Iianchao, Yu Kai, Gong Yihong, et al. Linear spatial pyramid matching using sparse coding for image classification [ C ]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. [ S. 1. ] :IEEE Press,2009:1794-1801. 被引量:1
  • 5Wang Jinjun, Yang .lianchao, Yu Kai, et al. Locality-constrained linear coding for image classification [ C ]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. [ S. 1. ] :IEEE Press ,2010 : 3360-3367. 被引量:1
  • 6Zhou Niu, Shen Yi, Peng J, et al. Learning inter-related visual dictio- nary for object recognition [ C ]//Proc of IEEE Conference on Comput- er Vision and Pattern Recognition. [ S. 1. ] :IEEE Press, 2012:3490- 3497. 被引量:1
  • 7Yang Liu, Jin Rong, Sukthankar R, et al. Unifying discriminative visualcodebook generation with classifier training for object category recognition[ c ]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. [ S. 1. ] :IEEE Press,2008:1-8. 被引量:1
  • 8谌先敢,刘娟,高智勇,刘海华.基于累积边缘图像的现实人体动作识别[J].自动化学报,2012,38(8):1380-1384. 被引量:15
  • 9王鑫,沃波海,管秋,陈胜勇.基于流形学习的人体动作识别[J].中国图象图形学报,2014,19(6):914-923. 被引量:30
  • 10Iosifidis A,Tefas A, Pitas I. View-invariant action recognition based on artificial neural networks[ J]. IEEE Trans on Neural Networks and Learning Systems,2012,23(3) :412-424. 被引量:1

二级参考文献171

  • 1Plagemann C, Ganapathi V, Koller D, et al. Real-time identification and localization of body parts from depth images[C]//Proceedings of IEEE International Conference on Robotics and Automation. Anchorage, USA: IEEE, 2010: 3108-3113. 被引量:1
  • 2Schwarz L A, Mkhitaryan A, Mateus D, et al. Estimating human 3d pose from time-of-flight images based on geodesic distances and optical flow[C]//Proceedings of IEEE International Conference on Automatic Face & Gesture Recognition and Workshops. Santa Barbara, USA: IEEE, 2011: 700-706. 被引量:1
  • 3Shotton J, Sharp T, Kipman A, et al. Real-time human pose recognition in parts from single depth images[J]. Communications of the ACM, 2013, 56(1): 116-124. 被引量:1
  • 4Sim D G, Kwon O K, Park R H. Object matching algorithms using robust Hausdorff distance measures[J]. IEEE Transactions on Image Processing, 1999, 8(3): 425-429. 被引量:1
  • 5Laptev I. On space-time interest points[J]. International Journal of Computer Vision, 2005, 64(2-3): 107-123. 被引量:1
  • 6Efros A A, Berg A C, Mori G, et al. Recognizing action at a distance[C]//Proceedings of IEEE International Conference on Computer Vision. Nice, France: IEEE, 2003: 726-733. 被引量:1
  • 7Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005, 1: 886-893. 被引量:1
  • 8Yang X, Zhang C, Tian Y L. Recognizing actions using depth motion maps-based histograms of oriented gradients[C]//Proceedings of ACM International Conference on Multimedia. New York, USA: ACM, 2012: 1057-1060. 被引量:1
  • 9Oreifej O, Liu Z, Redmond W A. HON4D: Histogram of oriented 4D normals for activity recognition from depth sequences[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Portland USA: IEEE, 2013: 716-723. 被引量:1
  • 10Reyes M, Domínguez G, Escalera S. Featureweighting in dynamic timewarping for gesture recognition in depth data[C]//Proceedings of IEEE International Conference on Computer Vision Workshops. Barcelona, Spain: IEEE, 2011: 1182-1188. 被引量:1

共引文献147

同被引文献18

引证文献3

二级引证文献2

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