首页 » 文章 » 文章详细信息
Journal of Electrical and Computer Engineering Volume 2017 ,2017-11-20
Improved Collaborative Representation Classifier Based on l2-Regularized for Human Action Recognition
Research Article
Shirui Huo 1 Tianrui Hu 2 Ce Li 3 , 4
Show affiliations
DOI:10.1155/2017/8191537
Received 2017-04-10, accepted for publication 2017-09-28, Published 2017-09-28
PDF
摘要

Human action recognition is an important recent challenging task. Projecting depth images onto three depth motion maps (DMMs) and extracting deep convolutional neural network (DCNN) features are discriminant descriptor features to characterize the spatiotemporal information of a specific action from a sequence of depth images. In this paper, a unified improved collaborative representation framework is proposed in which the probability that a test sample belongs to the collaborative subspace of all classes can be well defined and calculated. The improved collaborative representation classifier (ICRC) based on l2-regularized for human action recognition is presented to maximize the likelihood that a test sample belongs to each class, then theoretical investigation into ICRC shows that it obtains a final classification by computing the likelihood for each class. Coupled with the DMMs and DCNN features, experiments on depth image-based action recognition, including MSRAction3D and MSRGesture3D datasets, demonstrate that the proposed approach successfully using a distance-based representation classifier achieves superior performance over the state-of-the-art methods, including SRC, CRC, and SVM.

授权许可

Copyright © 2017 Shirui Huo et al. 2017
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

图表

Three DCNNs architecture for a depth action sequence to extract features.

Three DMMs of a depth action sequence “ASL Z” from the front (f) view, side (s) view, and top (t) view, respectively.

Three DMMs of a depth action sequence “Swipe left” from the front (f) view, side (s) view, and top (t) view, respectively.

Recognition rates (unit: %) of 20 classes in MSRAction3D dataset (average results of three subsets).

Recognition rates (unit: %) of 12 classes in MSRGesture3D dataset.

通讯作者

Ce Li.State Key Laboratory of Coal Resources and Safe Mining, China University of Mining & Technology, Beijing, China, cumt.edu.cn;University of Chinese Academy of Sciences, Beijing, China, ucas.ac.cn.licekong@gmail.com

推荐引用方式

Shirui Huo,Tianrui Hu,Ce Li. Improved Collaborative Representation Classifier Based on l2-Regularized for Human Action Recognition. Journal of Electrical and Computer Engineering ,Vol.2017(2017)

您觉得这篇文章对您有帮助吗?
分享和收藏
60

是否收藏?

参考文献
[1] W. Li, Z. Zhang, Z. Liu. Action recognition based on a bag of 3D points. :9-14. DOI: 10.1109/cvprw.2010.5543273.
[2] S. Wang, Z. Ma, Y. Yang, X. Li. et al.(2014). Semi-supervised multiple feature analysis for action recognition. IEEE Transactions on Multimedia.16(2):289-298. DOI: 10.1109/cvprw.2010.5543273.
[3] A. W. Vieira, E. R. Nascimento, G. L. Oliveira, Z. Liu. et al.(2014). On the improvement of human action recognition from depth map sequences using space-time occupancy patterns. Pattern Recognition Letters.36(1):221-227. DOI: 10.1109/cvprw.2010.5543273.
[4] J. Yang, J. Wright, T. Huang, Y. Ma. et al.Image super-resolution as sparse representation of raw image patches. :1-8. DOI: 10.1109/cvprw.2010.5543273.
[5] Y. Yang, B. Zhang, L. Yang, C. Chen. et al.Action recognition using completed local binary patterns and multiple-class boosting classifier. :336-340. DOI: 10.1109/cvprw.2010.5543273.
[6] J. Z. Huang, X. L. Huang, D. Metaxas. Simultaneous image transformation and sparse representation recovery. :1-8. DOI: 10.1109/cvprw.2010.5543273.
[7] L. Zhang, M. Yang, X. Feng. Sparse representation or collaborative representation: Which helps face recognition?. :471-478. DOI: 10.1109/cvprw.2010.5543273.
[8] W. Dong, L. Zhang, G. Shi, X. Wu. et al.(2011). Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Transactions on Image Processing.20(7):1838-1857. DOI: 10.1109/cvprw.2010.5543273.
[9] . DOI: 10.1109/cvprw.2010.5543273.
[10] A. Y. Yang, A. Genesh, Z. Zhou, S. Sastry. et al.(2010). A Review of Fast L1-Minimization Algorithms for Robust Face Recognition. Defense Technical Information Center. DOI: 10.1109/cvprw.2010.5543273.
[11] K. Huang, S. Aviyente. Sparse representation for signal classification. :609-616. DOI: 10.1109/cvprw.2010.5543273.
[12] A. Wagner, J. Wright, A. Ganesh, Z. Zhou. et al.Towards a practical face recognition system: Robust registration and illumination by sparse representation. :597-604. DOI: 10.1109/cvprw.2010.5543273.
[13] A. N. Tikhonov, V. Y. Arsenin. (1977). Solutions of Ill-Posed Problems. DOI: 10.1109/cvprw.2010.5543273.
[14] P. Berkes, B. L. White, J. Fiser. No evidence for active sparsification in the visual cortex. :108-116. DOI: 10.1109/cvprw.2010.5543273.
[15] B. Cheng, J. Yang, S. Yan, Y. Fu. et al.(2010). Learning with l1-graph for image analysis. IEEE Transactions on Image Processing.19(4):858-866. DOI: 10.1109/cvprw.2010.5543273.
[16] P. Wang, W. Li, Z. Gao, J. Zhang. et al.Deep convolutional neural networks for action recognition using depth map sequences. Computer Vision and Pattern Recognition. DOI: 10.1109/cvprw.2010.5543273.
[17] J. Wang, Z. Liu, J. Chorowski, Z. Chen. et al.(2012). Robust 3D action recognition with random occupancy patterns. Computer Vision—ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7–13, 2012, Proceedings, Part II:872-885. DOI: 10.1109/cvprw.2010.5543273.
[18] X. Yang, C. Zhang, Y. Tian. Recognizing actions using depth motion maps-based histograms of oriented gradients. :1057-1060. DOI: 10.1109/cvprw.2010.5543273.
[19] C. Chen, M. Liu, B. Zhang, J. Han. et al.3D action recognition using multi-temporal depth motion maps and fisher vector. :3331-3337. DOI: 10.1109/cvprw.2010.5543273.
[20] W. E. Vinje, J. L. Gallant. (2000). Sparse coding and decorrelation in primary visual cortex during natural vision. Science.287(5456):1273-1276. DOI: 10.1109/cvprw.2010.5543273.
[21] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry. et al.(2009). Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence.31(2):210-227. DOI: 10.1109/cvprw.2010.5543273.
[22] Q. Zhang, B. Li. Discriminative K-SVD for dictionary learning in face recognition. :2691-2698. DOI: 10.1109/cvprw.2010.5543273.
[23] E. Candès. Compressive sampling. .3:1433-1452. DOI: 10.1109/cvprw.2010.5543273.
[24] R. Vemulapalli, F. Arrate, R. Chellappa. Human action recognition by representing 3D skeletons as points in a lie group. :588-595. DOI: 10.1109/cvprw.2010.5543273.
[25] J.-L. Starck, M. Elad, D. Donoho. (2004). Redundant multiscale transforms and their application for morphological component separation. Advances in Imaging and Electron Physics.132:287-348. DOI: 10.1109/cvprw.2010.5543273.
[26] J. Yang, K. Yu, Y. Gong, T. Huang. et al.Linear spatial pyramid matching using sparse coding for image classification. :1794-1801. DOI: 10.1109/cvprw.2010.5543273.
[27] J. Wang, Z. Liu, Y. Wu, J. Yuan. et al.Mining actionlet ensemble for action recognition with depth cameras. :1290-1297. DOI: 10.1109/cvprw.2010.5543273.
[28] M. Yang, L. Zhang. Gabor feature based sparse representation for face recognition with gabor occlusion dictionary. :448-461. DOI: 10.1109/cvprw.2010.5543273.
[29] N. Guan, D. Tao, Z. Luo, B. Yuan. et al.(2012). NeNMF: an optimal gradient method for nonnegative matrix factorization. IEEE Transactions on Signal Processing.60(6):2882-2898. DOI: 10.1109/cvprw.2010.5543273.
[30] L. Xia, J. K. Aggarwal. Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera. :2834-2841. DOI: 10.1109/cvprw.2010.5543273.
文献评价指标
浏览 352次
下载全文 29次
评分次数 0次
用户评分 0.0分
分享 60次