期刊文献+

基于稀疏编码的时空金字塔匹配的动作识别 被引量:2

Spatio-temporal Pyramid Matching Using Sparse Coding for Action Recognition
下载PDF
导出
摘要 针对复杂场景下的动作识别,提出一种基于稀疏编码的时空金字塔匹配的动作识别方法.通过稀疏编码的方法学习更具有判别性的码书和计算局部块(cuboids)的稀疏表示;然后基于max pooling的时空金字塔匹配进行动作分类.该方法在KTH和YouTube两大公开数据集上进行了评价,实验结果表明,与基于K-means的时空金字塔匹配方法相比,该方法提高了2%-7%左右的识别率,在复杂的视频中取得了较好的识别效果. A spatio-temporal pyramid matching (STPM ) using sparse coding is proposed for action recognition in complex environment, which learns a more discriminative codebook and computes the cuboids'sparse representations by sparse coding followed by action classification using the STPM based on the max pooling. Experiments are evaluated on KTH and YouTube datasets. The results demonstrate that our approach achieves 2% to 7% improvement over the STPM based on k-means and obtains high recognition rate in complex videos.
出处 《小型微型计算机系统》 CSCD 北大核心 2012年第1期169-172,共4页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(60873192)资助 江西省教育厅科技项目(GJJ09143)资助 江西师范大学青年基金项目资助
关键词 动作识别 稀疏编码 时空金字塔匹配 词袋 action recognition sparse coding spatio-temporal pyramid matching bag of words
  • 相关文献

参考文献18

  • 1H, Battle A, Raina R, ctal. Efficient sparse coding algorithms [ C ]. Proceedings of Neural Information Processing Sys, terns, 2006:801-808. 被引量:1
  • 2DoLlar P, Rabaud V, Cottrcll G, et al. Behavior recognition via sparse spatio-temporal features[ C ]. Proceedings of IEEE International Workshop on VSPETS, 2005:65-72. 被引量:1
  • 3Schuldt C, l.,aptev I, Caputo B. Recognizing human actions: a local SVM approach [ C ]. Proceedings of the International Conference on Patuml Recognition, Los Alan~tos, C.alifomia, 2004:32-36. 被引量:1
  • 4Liu Jr Yang Y, Shah M. Learning semantic visual vocabularies using diffusion distance [ C ]. Proceedings of the Conference on Computer Vision and Pattern Recognition, Los Alamitos, California, 2009:461-468. 被引量:1
  • 5Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories [ C ]. Proceedings of the Conference on Computer Vision and Pattern Recognition, Los Alamitos, California, 2006:2169-2178. 被引量:1
  • 6杨跃东,郝爱民,褚庆军,赵沁平,王莉莉.基于动作图的视角无关动作识别[J].软件学报,2009,20(10):2679-2691. 被引量:5
  • 7Liu J, Shah M. Learning human actions via information maximization[C]. Proceedings of the Conference on Computer Vision and Pattern Recognition, Los Alamitos, California, 2008 : 1-8. 被引量:1
  • 8Laptev I. On space-time interest points[ J]. International Journal of Computer Vision, 2005,64(2-3 ) : 107-123. 被引量:1
  • 9Wong S, Kim T, CipoUa R. Learning motion categories using both somantics and structural information[ C]. Proceedings of the Conference on Computer Vision and Pattern Recognition, Los Alamitos, California, 2007 : 1-6. 被引量:1
  • 10Donoho D. For most large underdetermined systems of linear quation the minimal ll-norm solution is also the sparsest solution[ J]. Comm. on Pure and Applied Mathematics, 2006,59(6) :797-829. 被引量:1

二级参考文献15

  • 1Turaga P, Chellappa R, Subrahmanian V S, Udrea O. Machine recognition of human activities: A survey. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(11): 1473-1488. 被引量:1
  • 2Niebles J C, Wang H, Li Fei-Fei. Unsupervised learning of human action categories using spatial-temporal words. International Journal of Computer Vision, 2008, 79(3): 299-318. 被引量:1
  • 3Oliver N M, Rosario B, Pentland A P. A Bayesian computer vision system for modeling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8) : 831-843. 被引量:1
  • 4Xiang T, Gong S. Beyond tracking: Modeling activity and understanding behavior. International Journal of Computer Vision, 2006, 67(1): 21-51. 被引量:1
  • 5Ivanov Y A, Bobick A F. Recognition of visual activities and interactions by stochastic parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (8): 852-872. 被引量:1
  • 6Park S, Aggarwal J K. A hierarchical Bayesian network for event recognition of human action and interaction. ACM Journal of Multimedia Systems, Special Issue on Video Surveillance, 2004, 10(2): 164-179. 被引量:1
  • 7Ryoo M S, Aggarwal J K. Recognition of composite human activities through context-free grammar based representation//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. NY, USA, 2006, 1709-1719. 被引量:1
  • 8Du Y, Chen F, Xu W, Zhang W. Activity recognition through multi-scale motion detail analysis. Neurocomputing, 2008, 71(16-18): 3561-3574. 被引量:1
  • 9Hongeng S, Nevatia R, Bremond F. Video-hased event recognition: Activity representation and probabilistie reeognition methods. Computer Vision and Image Understanding, 2004, 96(2) : 129-162. 被引量:1
  • 10Hakeem A, Shah M. Learning, detection and representation of multi-agent event in videos. Artificial Intelligence, 2007, 171(8-9): 586-605. 被引量:1

共引文献27

同被引文献7

引证文献2

二级引证文献11

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