基于判别稀疏编码视频表示的人体动作识别

doi:10.3724/SP.J.1218.2012.00745

摘要
图/表
参考文献
相关文章 (3)

全文: PDF (1846 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
王斌, 王媛媛, 肖文华, 王炜, 张茂军 . 基于判别稀疏编码视频表示的人体动作识别[J]. 机器人, 2012, 34(6): 745-750,757.DOI: 10.3724/SP.J.1218.2012.00745. WANG Bin, WANG Yuanyuan, XIAO Wenhua, WANG Wei, ZHANG Maojun. Human Action Recognition Based on Discriminative Sparse Coding Video Representation. ROBOT, 2012, 34(6): 745-750,757. DOI: 10.3724/SP.J.1218.2012.00745.

摘要

为解决视频动作识别中“词袋”模型视频表示误差大、判别性弱，而影响人体动作识别精度的问题，本文提出判别稀疏编码视频表示算法：在稀疏编码框架下，引入Fisher判别分析，对视频局部时空特征编码，增强视频稀疏表示判别性．并提出在线判别字典学习算法，从海量视频数据中训练判别字典．实验表明，与现有算法相比，本文算法有效提高了人体动作识别精度．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王斌
	王媛媛
	肖文华
	王炜
	张茂军

关键词 ：动作识别, 词袋, 稀疏编码, Fisher判别准则

Abstract：

The bag-of-words (BoW) model usually causes large errors and weak discrimination in video representation in video action recognition, and affects the human action recognition accuracy. To solve this problem, a discriminative sparse coding (DSC) video representation algorithm is proposed. It's a sparse coding framework involving a Fisher discriminative analysis to encode video local spatial-temporal features and increase the video sparse representation discrimination. And an online discriminative dictionary learning algorithm is also proposed to train a dictionary from massive video data. The experiments show that, comparing with the existing algorithms, the proposed algorithm effectively improves human action recognition accuracy.

Key words： action recognition bag of words sparse coding Fisher discrimination criterion

收稿日期: 2012-05-15 录用日期: 2012-11-05

TP391

基金资助:

国家自然科学基金资助项目（61275016；61271438；61175006；61175015；60872150；60803101）

通讯作者: 王斌 E-mail: nudtwangbin@163.com

作者简介: 王斌（1983-），男，博士生．研究领域：计算机视觉与模式识别，稀疏表示，视频分析与理解．
王媛媛（1982-），女，硕士，讲师．研究领域：计算机视觉与模式识别．
肖文华（1988-），男，硕士生．研究领域：计算机视觉与模式识别，稀疏表示．

链接本文:

https://robot.sia.cn/CN/10.3724/SP.J.1218.2012.00745 或 https://robot.sia.cn/CN/Y2012/V34/I6/745

[1] Weinland D, Ronfard R, Boyer E. A survey of vision-based methods for action representation, segmentation and recognition[J]. Computer Vision and Image Understanding, 2011, 115(2): 224-241.

[2] Niebles J C, 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.

[3] Laptev I. On space-time interest points[J]. International Journal of Computer Vision, 2005, 64(2/3): 107-123.

[4] Escobar M J, Kornprobst P. Action recognition via bio-inspired features: The richness of center-surround interaction[J]. Computer Vision and Image Understanding, 2012, 116(5): 593-605.

[5] Wang H, Klaser A, Schmid C, et al. Action recognition by dense trajectories[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2011: 3169-3176.

[6] Yan X S, Luo Y P. Recognizing human actions using a new descriptor based on spatial-temporal interest points and weighted-output classifier[J]. Neurocomputing, 2012, 87(15): 51-61.

[7] Benmokhtar R. Robust human action recognition scheme based on high-level feature fusion[J/OL]. Multimedia Tools and Applications, 2012. [2012-04-10]. http://www.springerlink.com/content/m706w676h2906126/.

[8] Thi T H, Cheng L, Zhang J, et al. Integrating local action elements for action analysis[J]. Computer Vision and Image Understanding, 2012, 116(3): 378-395.

[9] Wang J, Chen Z Y, Wu Y. Action recognition with multiscale spatio-temporal contexts[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2011: 3185-3192.

[10] Ali S, Shah M. Human action recognition in videos using kinematic features and multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(2): 288-303.

[11] Yang J C, Yu K, Gong Y H, et al. Linear spatial pyramid matching using sparse coding for image classification[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2009: 1794-1801.

[12] Wang J J, Yang J C, Yu K, et al. Locality-constrained linear coding for image classification[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2010: 3360-3367.

[13] Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.

[14] Wright J, Ma Y, Mairal J, et al. Sparse representation for computer vision and pattern recognition[J]. Proceedings of the IEEE, 2010, 98(6): 1031-1044.

[15] Mairal J, Bach F, Ponce J, et al. Discriminative learned dictionaries for local image analysis[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2008: 1-8.

[16] Mairal J, Bach F, Ponce J, et al. Supervised dictionary learning[C]//Advances in Neural Information Processing Systems. Cambridge, CA, USA: MIT Press, 2009: 1033-1040.

[17] Mairal J, Leordeanu M, Bach F, et al. Discriminative sparse image models for class-specific edge detection and image interpretation[C]//European Conference on Computer Vision. Berlin, Germany: Springer-Verlag, 2008: 43-56.

[18] Boureau Y L, Bach F, LeCun Y,et al. Learning mid-level features for recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2010: 2559-2566.

[19] Zhang Q, Li B X. Discriminative K-SVD for dictionary learning in face recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2010: 2691-2698.

[20] Bishop C M. Pattern recognition and machine learning[M]. Berlin, Germany: Springer-Verlag, 2006: 186-189.

[21] Lee H, Battle A, Raina R, et al. Efficient sparse codingalgorithms[C]//Advances in Neural Information Processing Systems.Cambridge, CA, USA: MIT Press, 2007: 801-808.

[22] Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm fordesigning of overcomplete dictionaries for sparserepresentations[J]. IEEE Transactions on Signal Processing, 2006,54(11): 4311-4322.

[23] Mairal J, Bach F, Ponce J, et al. Online learning for matrix factorizationand sparse coding[J]. Journal of Machine Learning Research, 2010,11(3): 19-60.

[24] Mallat S G, Zhang Z F. Matching pursuits with time-frequencydictionaries[J]. IEEE Transactions on Signal Processing, 1993,41(12): 3397-3415.

[25] Laptev I, Marszalek M, Schmvol C, et al. Learning realistic human actions frommovies[C]//IEEE Conference on Computer Vision and PatternRecognition. Piscataway, NJ, USA: IEEE, 2008: 1-8.