A classification method based on streak flow for abnormal crowd behaviors

Abstract An abnormal crowd behavior would harm social public security. Different abnormal crowd behaviors would bring about different harms and subject to different attentions of social public. The higher the harm of the abnormal crowd behavior was, the higher the attention of the social public would be. Therefore, in this paper, a classification method, using crowd density estimation, is proposed for abnormal crowd behaviors. First, in order to enhance the accuracy of the abnormal crowd behavior detection, streak flow, based on fluid mechanics, is introduced to improve the algorithm proposed by Hassner et al. Second, the abnormal crowd behavior in a video scene is detected, the crowd density is estimated and the abnormal behavior is classified on the basis of the crowd density. Lastly, many challenging real-world surveillance videos are used to validate the effectiveness and feasibility of our method for abnormal behavior classification.

[1]  Amit K. Roy-Chowdhury,et al.  Vector field analysis for multi-object behavior modeling , 2013, Image Vis. Comput..

[2]  Ingo Roeder,et al.  A Fluid Registration Approach to Cell Tracking , 2013 .

[3]  Larry S. Davis,et al.  Unsupervised Abnormal Crowd Activity Detection Using Semiparametric Scan Statistic , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[4]  M. Nixon,et al.  On crowd density estimation for surveillance , 2006 .

[5]  Roberto Cipolla,et al.  Unsupervised Bayesian Detection of Independent Motion in Crowds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Leonidas J. Guibas,et al.  Counting people in crowds with a real-time network of simple image sensors , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Abishai Polus,et al.  Pedestrian Flow and Level of Service , 1983 .

[8]  Mubarak Shah,et al.  A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Mubarak Shah,et al.  A Streakline Representation of Flow in Crowded Scenes , 2010, ECCV.

[10]  Jarke J. van Wijk,et al.  Image based flow visualization , 2002, ACM Trans. Graph..

[11]  A. Marana,et al.  On the efficacy of texture analysis for crowd monitoring , 1998, Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237).

[12]  L. Li,et al.  On pixel count based crowd density estimation for visual surveillance , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[13]  Kristen Grauman,et al.  Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates , 2009, CVPR.

[14]  Nuno Vasconcelos,et al.  Bayesian Poisson regression for crowd counting , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[16]  Mubarak Shah,et al.  Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Hau-San Wong,et al.  Joint segmentation of collectively moving objects using a bag-of-words model and level set evolution , 2012, Pattern Recognit..

[18]  Xiaofei Wang,et al.  A high accuracy flow segmentation method in crowded scenes based on streakline , 2014 .

[19]  Ramin Mehran,et al.  Abnormal crowd behavior detection using social force model , 2009, CVPR.

[20]  Tal Hassner,et al.  Violent flows: Real-time detection of violent crowd behavior , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[21]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Sergio A. Velastin,et al.  Crowd monitoring using image processing , 1995 .

[23]  Nuno Vasconcelos,et al.  Privacy preserving crowd monitoring: Counting people without people models or tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Hai Tao,et al.  A Viewpoint Invariant Approach for Crowd Counting , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  Mubarak Shah,et al.  Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Marc Van Droogenbroeck,et al.  ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.

[27]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..