Pedestrian abnormal event detection based on multi-feature fusion in traffic video

Abstract Pedestrian abnormal event detection is an active research area to improve traffic safety for intelligent transportation systems (ITS). This paper proposes an efficient method to automatically detect and track far-away pedestrians in traffic video to determine the abnormal behavior events. Firstly, pedestrian features are extracted by the multi-feature fusion method. Then, the similar features in current frame of all candidate objects are matched with the characteristic information of pedestrians in the previous frame which is considered as a template. Finally, pedestrian trajectory analysis algorithms are employed on the tracking trajectories and the motion information is attained, which can realize the early classification warning of pedestrian events. Experimental results on different traffic scenes in practice demonstrate that this method has good robustness in complex traffic. Moreover, the proposed method performs better compared with some other methods.

[1]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Yu Jinwei,et al.  A model based method of pedestrian abnormal behavior detection in traffic scene , 2015, 2015 IEEE First International Smart Cities Conference (ISC2).

[3]  Keiichi Yamada,et al.  A shape-independent method for pedestrian detection with far-infrared images , 2004, IEEE Transactions on Vehicular Technology.

[4]  Jun Zhang,et al.  Detecting abnormal motion of pedestrian in video , 2008, 2008 International Conference on Information and Automation.

[5]  Jan Giebel,et al.  Shape-based pedestrian detection and tracking , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[6]  Kunio Fukunaga,et al.  Generating natural language description of human behavior from video images , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Hans P. Moravec.  Obstacle avoidance and navigation in the real world by a seeing robot rover , 1980 .

[8]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[9]  Farzin Mokhtarian,et al.  A Multi-Scale Approach to Corner Tracking , 2002, WSCG.

[10]  Vu-Duc Ngo,et al.  High throughput FPGA architecture for corner detection in traffic images , 2014, 2014 IEEE Fifth International Conference on Communications and Electronics (ICCE).

[11]  Tudor Barbu,et al.  Pedestrian detection and tracking using temporal differencing and HOG features , 2014, Comput. Electr. Eng..

[12]  Jong Seok Lim,et al.  Detecting and tracking of multiple pedestrians using motion, color information and the AdaBoost algorithm , 2012, Multimedia Tools and Applications.

[13]  Wei Yu,et al.  An active contour tracking method by matching foreground and background simultaneously , 2013, 2013 IEEE International Conference on Image Processing.

[14]  Tomaso A. Poggio,et al.  Example-Based Object Detection in Images by Components , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Tieniu Tan,et al.  Agent orientated annotation in model based visual surveillance , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[16]  X.B. Cao,et al.  Pedestrian Detection with Local Feature Assistant , 2007, 2007 IEEE International Conference on Control and Automation.

[17]  Bernd Neumann,et al.  On the Use of Motion Concepts for Top-Down Control in Traffic Scenes , 1990, ECCV.

[18]  Jing-Ming Chiu,et al.  Pedestrian tracking system by using human shape prior model , 2014, 2014 IEEE International Conference on Automation Science and Engineering (CASE).