Recognition of suspicious behavior using case-based reasoning

Abstract

A novel method case-based reasoning was proposed for suspicious behavior recognition. The method is composed of three departs: human behavior decomposition, human behavior case representation and case-based reasoning. The new approach was proposed to decompose behavior into sub-behaviors that are easier to recognize using a saliency-based visual attention model. New representation of behavior was introduced, in which the sub-behavior and the associated time characteristic of sub-behavior were used to represent behavior case. In the process of case-based reasoning, apart from considering the similarity of basic sub-behaviors, order factor was proposed to measure the similarity of a time order among the sub-behaviors and span factor was used to measure the similarity of duration time of each sub-behavior, which makes the similarity calculations more rational and comprehensive. Experimental results show the effectiveness of the proposed method in comparison with other related works and can run in real-time for the recognition of suspicious behaviors.

Keywords

visual attention mode / case-based reasoning / suspicious behavior / order factor / span factor

References

[1] KulicD, NakamuraY. Incremental learning of human behaviors using hierarchical hidden Markov models [C]. IEEE International Conference on Intelligent Robots and Systems, 2010, Taipei, Intelligent Robots and Systems (IROS): 4649-4655

[2] ZhouH-n, KimberD. Unusual event detection via multi-camera video mining [C]. 18th International Conference on Pattern Recognition, 2006, Hong Kong, CICPR: 1161-1166

[3] NaphadeM R, HuangT S. A probabilistic framework for semantic indexing and retrieval in video [C]. IEEE International Conference on Multimedia and Expo, 2000, New York, IEEE Press: 475-478

[4] NiuF, Abdel-MottalebM. HMM-based segmentation and recognition of human behaviors from video sequences [C]. IEEE International Conference on Multimedia and Expo, 2005, Amsterdam, IEEE Press: 804-807

[5] LiH-p, HuZ-y, WuY-h, WuF-chao. Behavior modeling and abnormality detection based on semi-supervised learning method [J]. Journal of Software, 2007, 18(3): 527-537

[6] ZhuX-d, LiuZ-jing. Human abnormal behavior recognition based on topic hidden Markov mode [J]. Computer Science, 2012, 39(3): 251-275

[7] XiangT, GongS G. Video behavior profiling and abnormality detection without manual labeling [C]. Proceedings of the IEEE International Conference on Computer Vision, 2005, Beijing, IEEE Press: 1238-1245

[8] ZhangJ, LiuZ-jing. A method of abnormal action recognition in variable scenarios [J]. Journal of Image and Graphics, 2009, 14(10): 2097-2101

[9] BregonzioM, GongS G, XiangT. Recognizing action as clouds of space-time interest points [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009, Miami, IEEE Press: 1948-1955

[10] RyooM S, AggarwalJ K. Recognition of composite human behaviors through context-free grammar based representation [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, New York, IEEE Computer Society: 1709-1718

[11] ElhamodM. Automated real-time detection of potentially suspicious behavior in public transport area [J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(2): 688-699

[12] ElhamodM, LevineM D. Real-time semantics-based detection of suspicious behaviors in public spaces [C]. 2012 Ninth Conference on Computer and Robot Vision, 2012, Toronto, IEEE Press: 268-275

[13] WiliemA, MadasuV, BolesW, YarcagaddaP K. A context-based approach for detecting suspicious behaviors [C]. Digital Image Computing: Techniques and Applications, 2009, Melbourne, IEEE Press: 156-153

[14] XiaL-m, HuangJ-x, TanL-zheng. Human action recognition based on chaotic invariants [J]. Journal of Central South University, 2013, 20(11): 3171-3179

[15] LaiJ-l, YiYang. Key frame extraction based on visual attention model [J]. Journal of Visual Communication and Image Representation, 2012, 23(1): 114-125

[16] IttiL, KochC. A saliency-based search mechanism for overt and covert shifts of visual attention [J]. Vision Research, 2000, 40(10/11/12): 1489-1506

[17] NieY, MaK H. Adaptive rood pattern search for fast block-matching motion estimation [J]. IEEE Transactions on Image Processing, 2002, 11(12): 1442-1449

[18] ParkS, AggarwalJ K. Simultaneous tracking of multiple body parts of interacting persons [J]. Computer Vision and Image Understanding, 2006, 102(1): 1-21

[19] ParkS, AggarwalJ K. Recognition of composite human behaviors through context-free grammar based representation [C]. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, New York, IEEE Press: 1709-1718

[20] VlachosM, KolliosG, GunopulosD. Discovering similar multidimensional trajectories[C]. 18th International Conference on Data Engineering, 2002, San Jose, IEEE Computer Society: 673-684

[21] CAVIAR test case scenarios [EB/OL]. 2004-01-17. http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIADATA1/.

[22] BEHAVE interactions test case scenarios [EB/OL]. 2007-10-05. http://groups.inf.ed.ac.uk/vision/BEHAVEDATA/INTERACTIONS/.

[23] StephenK, LorcanC, SimonD. Using ontologies in case-based behavior recognition [C]. Twenty-First International Artificial Intelligence Research Society Conference, 2010, Daytona, Association for the Advancement of Artificial Intelligence: 336-341

[24] WangT, SnoussiH. Histograms of optical flow orientation for visual abnormal events detection [C]. 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (AVSS), 2012, Beijing, IEEE Press: 13-18