{"title":"Automatic Motion Trajectory Analysis for Dual Human Interaction Using Video Sequences ","authors":"Yuan-Hsiang Chang, Pin-Chi Lin, Li-Der Jeng","volume":101,"journal":"International Journal of Computer and Information Engineering","pagesStart":1329,"pagesEnd":1337,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10001733","abstract":"
Advance in techniques of image and video processing has enabled the development of intelligent video surveillance systems. This study was aimed to automatically detect moving human objects and to analyze events of dual human interaction in a surveillance scene. Our system was developed in four major steps: image preprocessing, human object detection, human object tracking, and motion trajectory analysis. The adaptive background subtraction and image processing techniques were used to detect and track moving human objects. To solve the occlusion problem during the interaction, the Kalman filter was used to retain a complete trajectory for each human object. Finally, the motion trajectory analysis was developed to distinguish between the interaction and non-interaction events based on derivatives of trajectories related to the speed of the moving objects. Using a database of 60 video sequences, our system could achieve the classification accuracy of 80% in interaction events and 95% in non-interaction events, respectively. In summary, we have explored the idea to investigate a system for the automatic classification of events for interaction and non-interaction events using surveillance cameras. Ultimately, this system could be incorporated in an intelligent surveillance system for the detection and\/or classification of abnormal or criminal events (e.g., theft, snatch, fighting, etc.). <\/p>\r\n","references":"[1] S. Saravanakumar, A. Vadivel, and C. G. Saneem Ahmed, \u201cMultiple\r\nhuman object tracking using background subtraction and shadow removal\r\ntechniques,\u201d International Conference on Signal and Image Processing\r\n(ICSIP), pp. 79-84, 2010.\r\n[2] P. P. Kuralkar, and V. T. Gaikwad, \u201cHuman object tracking using\r\nbackground subtraction and shadow removal techniques,\u201d International\r\nJournal of Advanced Research in Computer Science and Software\r\nEngineering, vol. 2, no. 3, March 2012.\r\n[3] F. Porikli, and O. Tuzel, \u201cHuman body tracking by adaptive background\r\nmodels and mean-shift analysis,\u201d IEEE International Workshop on\r\nPerformance Evaluation of Tracking and Surveillance, 2003.\r\n[4] P. Banerjee, and S. Sengupta, \u201cHuman motion detection and tracking for\r\nvideo surveillance,\u201d Proceedings of the national Conference of\r\nCommunications, IIT Bombay, Mumbai, pp. 88-92, 2008.\r\n[5] R. S. Rakibe, and B. D. Patil, \u201cBackground subtraction algorithm based\r\nhuman motion detection,\u201d International Journal of Scientific and\r\nResearch Publications, vol. 3, no.5, 2013.\r\n[6] W. Kim, and J. Lee, \u201cVisual tracking using Snake based on target's\r\ncontour information,\u201d Industrial Electronics, Proceedings. ISIE 2001.\r\nIEEE International Symposium on IEEE, vol. 1, pp. 176-180, 2001.\r\n[7] D. Comaniciu, V. Ramesh, and P. Meer, \u201cKernel based object tracking,\u201d\r\nIEEE Transactions on Pattern Analysis Machine Intelligence, vol. 25,\r\nno.5, pp. 564-557, 2003.\r\n[8] F. Chang, L. Ma, and Y. Qiao, \u201cTarget tracking under occlusion by\r\ncombining Integral-Intensity-Matching with multi-block-voting,\u201d in\r\nProc. of Lecture Notes, vol. 3644, pp. 77-86, 2005.\r\n[9] P. F. Gabriel, et al., \u201cThe state of the art in multiple object tracking under\r\nocclusion in video sequences,\u201d Advanced Concepts for Intelligent Vision\r\nSystems, pp. 166-73, 2003.\r\n[10] Z. Li, A.K. Katsaggelos and B.Gandhi, \u201cFast video shot retrieval based on\r\ntrace geometry matching,\u201d IEE Proc.-Vis. Image Signal Process., vol.\r\n152, no. 3, June 2005.\r\n[11] H.-Y. M. Liao, D.-Y. Chen, C.-W. Su and H.-R. Tyan, \u201cReal-time event\r\ndetection and its application to surveillance systems,\u201d Proceedings of\r\nIEEE International Symposium on Circuits and Systems, ISCAS, pp. 509\r\n-512, 2006.\r\n[12] D. H. Douglas and T. K. Peucker, \u201cAlgorithms for the reduction of the\r\nnumber of points required to represent a digitized line or its caricature,\u201d\r\nThe Canadian Cartographer, vol. 10, no. 2, pp. 112-122, 1973.\r\n[13] Y. Zhou and T. S. Huang, \u201c\u2019Bag of segments\u2019 for motion trajectory\r\nanalysis,\u201d 15th IEEE International Conference on Image Processing,\r\nICIP, pp. 757-760, 2008.\r\n[14] H.-I. Suk, A.K. Jaim and S.-W. Lee, \u201cA Network of Dynamic\r\nProbabilistic Models for Human Interaction Analysis,\u201d IEEE\r\nTransactions on Circuits and Systems for Video Technology, vol. 21, no.\r\n7, July 2011.\r\n[15] H. Habe, K. Honda and M. Kidode, \u201cHuman Interaction Analysis Base on\r\nWalking Pattern Transitions,\u201d Third ACM\/IEEE International\r\nConference on Distributed Smart Cameras, ICDSC, pp. 1-8, 2009.\r\n[16] N. Otsu, \u201cA threshold selection method from gray-Level histogram,\u201d\r\nIEEE Trans. Systems, Man and Cybernetics, vol. 9, no.1, pp. 62-66, 1979.\r\n[17] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2rd Edition.\r\nNew York: Prentice Hall, 2002.\r\n[18] H. Freeman, Boundary Encoding and Processing, in Picture Processing\r\nand Psychopictorics, B S Lipkin and A Rosenfeld, Editors, Academic\r\nPress: New York. pp. 241-266, 1970.\r\n[19] P. F. Felzensz and D. P. Huttenlocher, \u201cDistance transforms of sampled\r\nfunctions,\u201d Techniacl Report TR2004-1963, Computer Science\r\nDepartment, Cornell University, September 2004.\r\n[20] R. E. Kalman, \u201cA new approach to linear filtering and prediction\r\nproblems,\u201d Journal of basic Engineering, vol. 82, no. 1, pp. 35-45, 1960. ","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 101, 2015"}