Human Action Recognition Algorithm Based on Selective Ensemble Rotation Forest
TANG Chao1, WANG Wenjian2, LI Wei3 , LI Guobin1, CAO Feng2, ZHANG Miaohui4
1.Department of Computer Science and Technology, Hefei University, Hefei 230601 2.School of Computer and Information Technology, Shanxi University, Taiyuan 030006 3.College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361005 4.Energy Research Institute, Jiangxi Academy of Sciences, Nanchang 330096
Abstract The representation of high dimensional human actions and the construction of accurate and stable human classification model are key issues in human action recognition. An efficient action recognition algorithm based on mixed features is proposed. Key joints of human body polar coordinates features based on appearance structure and motion features based on optical flow are fused into the proposed algorithm to capture motion information in video sequences and improve the recognition instantaneity. Meanwhile, the selective ensemble rotation forest model (SERF) based on frame is developed and the selection ensemble strategy is used to select the base classifier of rotation forest and increase differences among the classifiers. Experimental results show the better classification accuracy and robustness of the proposed model.
Fund:Supported by National Natural Science Foundation of China (No.41401521,61273291), Overseas Returnee Research Fund in Shanxi Province (No.2012-008), Shanxi Province Natural Science Foundation for Youths (No.2015021101), Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province (No.2014001), Natural Science Research Project of Universities of Anhui Province (No.KJ2015A206), Scientific Research Fund Project of Talents of Hefei University (No.15RC07), Key Constructive Discipline Project of Hefei University (No.2014xk08), Training Object Project for Academic Leader of Hefei University (No.2014dtr08), High-Level Talent Funds of Xiamen University of Technology (No.YKJ14014R)
About author:: (TANG Chao(Corresponding author)， born in 1977， Ph.D.， lecturer. His research interests include machine learning and computer vision.) (WANG Wenjian， born in 1968， Ph.D.， professor. Her research interests include machine learning and computer intelligence.)
(LI Wei， born in 1979， Ph.D.， associate professor. His research interests include artificial intelligence， computer graphics and human computer interaction.) (LI Guobin， born in 1981， master， experimentalist. His research interests include machine learning.) (CAO Feng， born in 1980， Ph.D.， lecturer. His research interests include machine learning and data mining.) (ZHANG Miaohui， born in 1987， Ph.D.， assistant resear-cher. His research interests include visual search and human action recognition.)
[1] HASSNER T. A Critical Review of Action Recognition Benchmarks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Portland, USA, 2013: 245-250. [2] AGGARWAL J K, RYOO M S. Human Activity Analysis: A Review. ACM Computing Surveys, 2011, 43(3): 194-218. [3] CHAQUET J M, CARMONA E J, FERNNDEZ-CABALLERO A. A Survey of Video Datasets for Human Action and Activity Recognition. Computer Vision and Image Understanding, 2013, 117(6): 633-659. [4] ROSE M S D, WAGNER C C. Survey on Classifying Human Actions through Visual Sensors. Artificial Intelligence Review, 2012, 37(4): 301-311. [5] IOSIFIDIS A, TEFAS A, PITAS I. Multi-view Human Action Re-cognition: A Survey // Proc of the 9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Beijing, China, 2013: 522-525. [6] LIM C H, VATS E, CHAN C S. Fuzzy Human Motion Analysis: A Review. Pattern Recognition, 2015, 48(5): 1773-1796. [7] WEINLAND D, RONFARD R, BOYER E. A Survey of Vision-Based Methods for Action Representation, Segmentation and Recognition. Computer Vision and Image Understanding, 2011, 115(2): 224-241. [8] 李瑞峰,王亮亮,王 珂.人体动作行为识别研究综述.模式识别与人工智能, 2014, 27(1): 35-48. (LI R F, WANG L L, WANG K. A Survey of Human Body Action Recognition. Pattern Recognition and Artificial Intelligence, 2014, 27(1): 35-48.) [9] ZHONG J, LIU H W, LIN C L. Human Action Recognition Based on Hybrid Features. Applied Mechanics and Materials, 2013. DOI:10.4028/www.scientific.net/AMM.373-375.1188. [10] LIU S, LIU J, ZHANG T Z, et al. Human Action Recognition in Videos Using Hybrid Motion Features // Proc of the 16th International Conference on Multimedia Modeling. Chongqing, China, 2010: 411-421. [11] LIU X P, LI Y B. Research on Human Action Recognition Based on Global and Local Mixed Features // Proc of the International Conference on Mechatronics, Control and Electronic Engineering. Shenyang, China, 2014: 692-696. [12] VO V, LY N. Robust Human Action Recognition Using Improved BOW and Hybrid Features // Proc of the IEEE International Symposium on Signal Processing and Information Technology. Ho Chi Minh City, Vietnam, 2012: 224-229. [13] ZHANG H B, SU S Z, LI S Z, et al. Seeing Actions through Scene Context // Proc of the IEEE International Conference on Visual Communications and Image Processing. Kuching, Malaysia, 2013. DOI:10.1109/VCIP.2013.6706382. [14] HALL D L, LLINAS J. An Introduction to Multisensor Data Fusion. Proceedings of IEEE, 1997, 85(1): 6-23. [15] 于成龙.基于视频的人体行为识别关键技术研究.博士学位论文.哈尔滨:哈尔滨工业大学, 2013. (YU C L. Research on Key Technologies of Video-Based Human Behavior Recognition. Ph. D Dissertation. Harbin, China: Harbin Institute of Technology, 2013.) [16] YANG J, YANG J Y, ZHANG D, et al. Feature Fusion: Parallel Strategy vs. Serial Strategy. Pattern Recognition, 2003, 36(6): 1369-1381. [17] RODRIGUEZ J J, KUNCHEVA L I, ALONSO C J. Rotation Fo-rest: A New Classifier Ensemble Method. IEEE Trans on Pattern Analysis and Machine Intelligence, 2006, 28(10): 1619-1630. [18] 张春霞,张讲社.选择性集成学习算法综述.计算机学报, 2011, 34(8): 1399-1410. (ZHANG C X, ZHANG J S. A Survey of Selective Ensemble Learning Algorithms. Chinese Journal of Computers, 2011, 34(8): 1399-1410.) [19] WOZ/NIAK M, GRAN~A M, CORCHADO E. A Survey of Multiple Classifier Systems as Hybrid Systems. Information Fusion, 2014, 16: 3-17. [20] DOLLR P, RABAUD V, COTTRELL G, et al. Behavior Recognition via Sparse Spatio-Temporal Features // Proc of the IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Beijing, China, 2005: 65-72. [21] NIEBLES J C, WANG H C, LI F F. Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. International Journal of Computer Vision, 2008, 79(3): 299-318.
2016, Vol. 29 
