Human Activity Recognition Based on Combined SVM&HMM

doi:10.3969/j.issn.1006-2475.2015.05.001

Abstract

Abstract: Being able to recognize human activities is essential for several intelligent applications, including personal assistive robotics and smart homes. In this paper, we perform the recognition of the human activity based on the combined SVM&HMM in daily living environments. Firstly, we use a RGBD sensor (Microsoft Kinect) as the input sensor, and extract a set of the fusion features, including motion, body structure features and joint polar coordinates features. Secondly, we propose a combined SVM&HMM model which not only combines the SVM characteristics of reflecting the difference among the samples, but also develops the HMM characteristics of dealing with the continuous activities. The SVM&HMM model plays their respective advantages of SVM and HMM comprehensively. Thus, the combined model overcomes the drawbacks of accuracy, robustness and computational efficiency compared with the separate SVM model or the traditional HMM model in the human activity recognition. The experiment results show that the proposed algorithm possesses the better robustness and distinction.

Key words: Kinect, activity recognition, fusion features, SVM, HMM

CLC Number:

TP391

SU Hong-yu1, CHEN Qi-an1, WU Hai-tao2. Human Activity Recognition Based on Combined SVM&HMM[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2015.05.001.

References

[1] Ning Huazhong, Han Tony Xu, Walther D B, et al. Hierarchical space-time model enabling efficient search for human actions[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009,19(6):808-820.

[2] Gupta A, Srinivasan P, Shi Jianbo, et al. Understanding videos, constructing plots: Learning a visually grounded storyline model from annotated videos[C]// Proceedings of the 2009 IEEE International Conference on Computer Vision and Pattern Recognition. 2009:2012-2019.

[3] Wu Jianxin, Osuntogun A, Choudhury T, et al. A scalable approach to activity recognition based on object use[C]// Proceedings of the 11th IEEE International Conference on Computer Vision. 2007.

[4] Liu Jingen, Ali S, Shah M. Recognizing human actions using multiple features[C]// Proceedings of the 2008 IEEE International Conference on Computer Vision and Pattern Recognition. 2008.

[5] Yao Bangpeng, Li Feifei. Modeling mutual context of object and human pose in human-object interaction activities[C]// Proceedings of the 2010 IEEE International Conference on Computer Vision and Pattern Recognition. 2010:17-24.

[6] Aksoy E, Abramov A, Worgotter F, et al. Categorizing object-action relations from semantic scene graphs[C]// Proceedings of the 2010 IEEE International Conference on Robotics and Automation. 2010:398-405.

[7] Jiang Yugang, Li Zhenguo, Chang Shih-Fu. Modeling scene and object contexts for human action retrieval with few examples[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011,21(5):674-681.

[8] Pirsiavash H, Ramanan D. Detecting activities of daily living in first-person camera views[C]// Proceedings of the 2012 IEEE International Conference on Computer Vision and Pattern Recognition. 2012:2847-2854.

[9] Li Wanqing, Zhang Zhengyou, Liu Zicheng. Action recognition based on a bag of 3D points[C]// Proceedings of the 3rd IEEE International Workshop on CVPR for Human Communicative Behavior Analysis. 2010:9-14.

[10] Sung J, Ponce C, Selman B, et al. Human activity detection from RGBD images[C]// Proceedings of the 2011 AAAI Workshop on Pattern, Activity and Intent Recognition (PAIR). 2011.

[11] Sung J, Ponce C, Selman B, et al. Unstructured human activity detection from RGBD images[C]// Proceedings of the 2012 IEEE International Conference on Robotics and Automation. 2012:842-849.

[12] Zhang H, Parker L. 4-dimensional local spatio-temporal features for human activity recognition[C]// Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2011:2044-2049.

[13] Johansson G. Visual perception of biological motion and a model for its analysis[J]. Perception and Psychophysics, 1973,14(2):201-211.

[14] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995,20(3):273-297.

[15] Baum L E. An equality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes[J]. Inequalities, 1972,3:1-8.

[16] Baum L E, Egon J A. An inequality with applications to statistical estimation for probabilistic functions of a Markov process and to a model for ecology[J]. Bulletin of the American Meteorological Society, 1967,73(2):360-363.

[17] 忻栋,杨莹春,吴朝晖. 基于SVM-HMM混合模型的说话人确认[J]. 计算机辅助设计与图形学学报, 2002,14(11):1080-1082.

[18] Piyathilaka L, Kodagoda S. Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features[C]// Proceedings of the 8th IEEE International Conference on Industrial Electronics and Applications (ICIEA). 2013:567-572.

[19] Zhang Chenyang, Tian Yingli. RGB-D camera-based daily living activity recognition[J]. Journal of Computer Vision and Image Processing, 2012,2(4):12.

[20] 田原,谭铁牛,孙洪赞. 一种具有良好鲁棒性的实时跟踪方法[J]. 自动化学报, 2002,28(5):851-853.

[21] 余涛,叶金永,邵菲杰,等. Kinect核心技术之骨架追踪技术[J]. 数字技术与应用, 2012(10):115.

[22] 亓磊. 基于隐马尔可夫模型的步态识别算法研究[D]. 济南:山东大学, 2008.

[23] 苏毅,吴文虎,郑方,等. 基于支持向量机的语音识别研究[C]// 第六届全国人机语音通讯学术会议论文集. 2001:223-226.