Human behavior recognition based on the statistical characteristics of gradient and optical flow

被引：0

作者：

Zhang, Fei-Yan ^{[1
]}

Li, Jun-Feng ^{[1
]}

Shen, Jun-Min ^{[2
]}

机构：

[1] Department of Automation, Zhejiang University of Science and Technology, Hangzhou

[2] Department of Electronic Information Engineering, Zhejiang University of Science and Technology, Hangzhou

来源：

Guangdianzi Jiguang/Journal of Optoelectronics Laser | 2015年 / 26卷 / 08期

关键词：

Asymmetric generalized Gaussian distribution (AGGD); Gradient; Human behavior recognition; Optical flow;

D O I：

10.16136/j.joel.2015.08.0041

中图分类号：

学科分类号：

摘要：

Through the analysis of histogram distribution of the local spatio-temporal features (gradient and optical flow) for different behavior videos, it is found that the statistics characteristics of gradient and optical flow for different behavior videos are obviously different respectively. In order to ensure the high descriptive of features to the behavior, a new method of human activity recognition is put forward by using the statistics characteristics of gradient and optical flow in this paper. Firstly, it is found that the histogram distributions of gradient and optical flow for different behavior videos conform to the asymmetric generalized Gaussian distribution (AGGD) through the mathematical statistic analysis. Secondly, the parameters of AGGD model are extracted respectively and fused to describe different behavior as the statistical features. Moreover, human behavior is recognized through calculating the Mahalanobis distance between the test video's feature matrix and the train videos'. Finally, the performance is investigated in the KTH action dataset and Weizmann action dataset, and the average recognition rates are as high as 93.16% and 95.20% for the two action datasets, respectively. The results show that this method can generate a more comprehensive and effective representation for action videos. ©, 2015, Board of Optronics Lasers. All right reserved.

引用

页码：1593 / 1601

页数：8

共 27 条

[1]

Li R.-F., Wang L.-L., Wang K., A survey of human body action recognition, Pattern Recognition and Artificial Intelligence, 27, 1, pp. 35-48, (2014)

[2]

Boisvert J., Shu C., Wuhrer S., Et al., Three-dimensional human shape inference from silhouettes: Reconstruction and validation, Machine Vision and Applications, 24, 1, pp. 145-157, (2013)

[3]

Wu D., Shao L., Silhouette analysis-based action recognition via exploiting human poses, IEEE Transactions on Circuits and Systems for Video Technology, 23, 2, pp. 236-243, (2013)

[4]

Vishwakarma, Agrawal A., A survey on activity recognition and behavior understanding in video surveillance, The Visual Computer, 29, 10, pp. 983-1009, (2013)

[5]

Parvathy R., Thilakan S., Joy M., Et al., Anomaly detection using motion patterns computed from optical flow, Proc. of IEEE International Conference on Computer Society, pp. 58-61, (2013)

[6]

Shao Y.-H., Guo Y.-C., Gao C., Human action recognition using multi-feature fusion, Journal of Optoelectronics · Laser, 25, 9, pp. 1818-1823, (2014)

[7]

Chaudhry R., Avichandran A., Hager G., Et al., Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions, Proc. of IEEE International Conference on Computer Society, pp. 1932-1939, (2009)

[8]

Laptev I., Marszalek M., Schmid C., Et al., Learning realistic human actions from movies, Proc. of IEEE International Conference on Computer Vision and Patter, pp. 1-8, (2008)

[9]

Salmane H., Ruichek Y., Khoudour L., Object tracking using Harris corner points based optical flow propagation and Kalman filter, Proc. of IEEE International Conference on Intelligent Transportation Syst, pp. 67-73, (2011)

[10]

Dollar P., Rabaud V., Cottrell G., Et al., Behavior recognition via sparse spatio-temporal features, Proc. of IEEE International Conference on Workshop, pp. 65-72, (2005)

← 1 2 3 →