Abstract A key frames based method is proposed for recognition of complex human behavior. The body contours are adopted to represent actions. The complex behavior fragment is divided into simple behaviors by the shot boundary detection algorithm. To improve the recall rate, double sampling is employed during the segmentation. The self-splitting competitive learning algorithm is utilized to acquire key frames of simple behaviors. Finally, the recognition of complex human behavior is achieved according to the similarity of the key frames. During the process, the visual factor, the order factor and the interference factor are taken into account. Thus, the calculations of the recognition are more rational and comprehensive. The proposed method is verified on UCF Sports database and self-built database and the results indicate the high recognition accuracy of the proposed method.
[1] BURGHOUTS G J, SCHUTTE K, BOUMA H, et al. Selection of Negative Samples and Two-Stage Combination of Multiple Features for Action Detection in Thousands of Videos. Machine Vision and Applications, 2014, 25(1): 85-98. [2] KHOSHHAL K, ALIAKBARPOUR H, MEKHNACHA K, et al. LMA-Based Human Behaviour Analysis Using HMM // Proc of the 2nd IFIP WG 5.5/SOCOLNET Doctoral Conference on Computing, Electrical and Industrial Systems. Costa da Caparica, Portugal, 2011: 189-196. [3] NATARAJAN P, NEVATIA R. Coupled Hidden Semi Markov Models for Activity Recognition // Proc of the IEEE Workshop on Motion and Video Computing. Austin, USA, 2007. DOI: 10.1109/WMVC.2007.12. [4] HOSPEDALES T M, LI J, GONG S G, et al. Identifying Rare and Subtle Behaviors: A Weakly Supervised Joint Topic Model. IEEE Trans on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2451-2464. [5] FU Y W, HOSPEDALES T M, XIANG T, et al. Attribute Learning for Understanding Unstructured Social Activity // Proc of the 12th European Conference on Computer Vision. Florence, Italy, 2012, IV: 530-543. [6] BANDOUCH J, JENKINS O C, BEETZ M. A Self-training Approach for Visual Tracking and Recognition of Complex Human Activity Patterns. International Journal of Computer Vision, 2012, 99(2): 166-189. [7] FERNNDEZ-CABALLERO A, CASTILLO J C, RODRGUEZ-SNCHEZ J M. Human Activity Monitoring by Local and Global Finite State Machines. Expert Systems with Applications, 2012, 39(8): 6982-6993. [8] SANROM G, BURGHOUTS G, SCHUTTE K. Recognition of Long-Term Behaviors by Parsing Sequences of Short-Term Actions with a Stochastic Regular Grammar // Proc of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition. Hiroshima, Japan, 2012: 225-233. [9] OUANANE A, SERIR A. New Paradigm for Recognition of Aggre-ssive Human Behavior Based on Bag-of-Features and Skeleton Graph // Proc of the 8th International Workshop on Systems, Signal Processing and Their Applications. Algiers, Algeria, 2013: 133-138. [10] LIN S Y, SHIE C K, CHEN S C, et al. Human Action Recognition Using Action Trait Code // Proc of the 21st International Confe-rence on Pattern Recognition. Tsukuba, Japan, 2012: 3456-3459. [11] LIU A, SU Y T, JIA P P, et al. Multiple/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning. IEEE Trans on Cybernetics, 2014, 45(6): 1194-1208. [12] 黄金霞.基于SCFG的复杂人体行为识别.硕士学位论文.长沙:中南大学, 2013. (HUANG J X. Complex Human Activity Recognition Based on SCFG. Master Dissertation. Changsha, China: Central South University, 2013.) [13] MIN H S, NEVE W D, RO Y M. Sparse Representation-Based Human Action Recognition Using an Action Region-Aware Dictionary // Proc of the IEEE International Symposium on Multimedia. Anaheim, USA, 2013: 133-139. [14] KE S R, THUC H L U, LEE Y J, et al. A Review on Video-Based Human Activity Recognition. Computers, 2013, 2(2): 88-131. [15] ZIVKOVIC Z, VAN DER HEIJDEN F. Efficient Adaptive Density Estimation per Image Pixel for the Task of Background Subtraction. Pattern Recognition Letters, 2006, 27(7): 773-780. [16] 赵亚琴,周献中,何 新.利用等价关系理论进行视频片段检索的方法.中国图象图形学报, 2007, 12(1): 127-134. (ZHAO Y Q, ZHOU X Z, HE X. An Efficient Method for Video Clip Retrieval Using Equivalence Relation Theory. Journal of Image and Graphics, 2007, 12(1): 127-134.) [17] 李卫伟,刘纯平,王朝晖,等.基于SSCL的模糊C均值图像分类方法.中国图象图形学报, 2011, 16(2): 215-220. (LI W W, LIU C P, WANG Z H, et al. Fuzzy C-means Image Classification Algorithm Based on SSCL. Journal of Image and Gra-phics, 2011, 16(2): 215-220.) [18] 肖永良.基于内容的视频检索关键技术研究.博士学位论文.长沙:中南大学, 2010. (XIAO Y L. Research on Some Key Techniques of Content Based Video Retrieval. Ph.D Dissertation. Changsha, China: Central South University, 2010.) [19] BIRINCI M, KIRANYAZ S. A Perceptual Scheme for Fully Automatic Video Shot Boundary Detection. Signal Processing: Image Communication, 2014, 29(3): 410-423. [20] RYOO M S, AGGARWAL J K. Recognition of Composite Human Activities through Context-Free Grammar Based Representation // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition. New York, USA, 2006, II: 1709-1718.
2016, Vol. 29 
