计算机科学 ›› 2017, Vol. 44 ›› Issue (7): 270-274.doi: 10.11896/j.issn.1002-137X.2017.07.048
季冲,王胜,陆建峰
JI Chong, WANG Sheng and LU Jian-feng
摘要: 人体行为识别是计算机视觉中的一个重要研究领域,具有广阔的应用前景。研究了基于Fisher鉴别的字典学习方法在人体行为识别上的应用。首先对人体行为的视频序列提取了局部时空特征,并通过随机投影法降维;然后把降维后的特征作为待分类的信号进行Fisher鉴别字典学习,从而增强字典和编码系数的鉴别能力;最后同时利用重构误差和稀疏表示系数进行分类。实验结果验证了所提方法在人体行为识别上的有效性与鲁棒性。
[1] POPPE R.A survey on vision-based human action recognition[J].Image and Vision Computing,2010,28(6):976-990. [2] HU Q,QIN L,HUANG Q M.A Survey on Visual Human Action Recognition[J].Chinese Journal of Computers,2013,36(12):2512-2524.(in Chinese) 胡琼,秦磊,黄庆明.基于视觉的人体行为识别综述[J].计算机学报,2013,36(12):2512-2524. [3] GUHA T,WARD R K.Learning sparse representations for human action recognition[J].IEEE Transactions on Pattern Ana-lysis and Machine Intelligence,2012,34(8):1576-1588. [4] YUAN C,HU W,TIAN G,et al.Multi-task Sparse Learning with Beta Process Prior for Action Recognition[J].IEEE Conference on Computer Vision & Pattern Recognition,2013,9(4):423-429. [5] WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227. [6] AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322. [7] PATI Y C,REZAIIFAR R,KRISHNAPRASAD P S.Orthogonal matching pursuit:Recursive function approximation with applications to wavelet decomposition[C]∥Conference Record of The Twenty-Seventh Asilomar Conference on Signals,Systems and Computers.1993:40-44. [8] GORELICK L,BLANK M,SHECHTMAN E,et al.Actions as space-time shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(12):2247-2253. [9] BARANIUK R,WAKIN M.Random Projections of SmoothManifolds[J].Foundations of Computational Math,2009,9(1):51-77. [10] RUBINSTEIN R,ZIBULEVSKY M,ELAD M.Efficient Implementation of the K-SVD Algorithm Using Batch Orthogonal Matching Pursuit[R].Haifa,Israel:Israel Institute of Technology,2008. [11] YANG M,ZHANG L,FENG X,et al.Fisher DiscriminationDictionary Learning for sparse representation[J].International Conference on Computer Vision,2011,24(4):543-550. [12] SCOVANNER P,ALI S,SHAH M.A 3-dimensional sift de-scriptor and its application to action recognition[C]∥Procee-dings of the 15th international conference on Multimedia.ACM,2007:357-360. [13] KLASER A,MARSZALEK M.A spatio-temporal descriptor based on 3D-gradients[C]∥Proceedings of the British Machine Vision Conference.2008:995-1004. [14] ZHANG Z,HU Y,CHAN S, et al.Motion Context:A NewRepresentation for Human Action Recognition[C]∥Procee-dings of the 10th European Conference on Computer Vision.2008:817-829. [15] SEO H J,MILANFAR P.Action recognition from one example[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):867-882. [16] NIEBLES JC,WANG H,LI F F.Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words[J].International Journal of Computer Vision,2008,79(3):299-318. [17] ZHANG Q,LI B.Discriminative K-SVD for dictionary learning in face recognition[J].IEEE Conference on Computer Vision & Pattern Recognition,2010,119(5):2691-2698. [18] YANG J,YU K,HUANG T.Supervised Translation-InvariantSparse coding[J].IEEE Conference on Computer Vision & Pattern Recognition,2010,26(2):3517-3524. [19] RAMIREZ I,SPRECHMANN P,SAPIRO G.Classification and clustering via dictionary learning with structured incoherence and shared features[J].IEEE Conference on Computer Vision& Pattern Recognition,2010,23(3):3501-3508. [20] WANG B,WANG Y Y,XIAO W H,et al.Human Action Re-cognition Based on Discriminative Sparse Coding Video Representation[J].Robot,2012,34(6):745-750.(in Chinese) 王斌,王媛媛,肖文华,等.基于鉴别稀疏编码视频表示的人体动作识别[J].机器人,2012,34(6):745-750. [21] ROSASCO L,VERRI A,SANTORO M,et al.Iterative Projection Methods for Structured Sparsity Regularization[R].Massachusetts:Massachusetts Institute of Technology,2009. |
No related articles found! |
|