Effective Crowd Anomaly Detection Through Spatio-temporal Texture Analysis

Abnormal crowd behaviors in high density situations can pose great danger to public safety. Despite the extensive installation of closed-circuit television (CCTV) cameras, it is still difficult to achieve real-time alerts and automated responses from current systems. Two major breakthroughs have been reported in this research. Firstly, a spatial-temporal texture extraction algorithm is developed. This algorithm is able to effectively extract video textures with abundant crowd motion details. It is through adopting Gabor-filtered textures with the highest information entropy values. Secondly, a novel scheme for defining crowd motion patterns (signatures) is devised to identify abnormal behaviors in the crowd by employing an enhanced gray level co-occurrence matrix model. In the experiments, various classic classifiers are utilized to benchmark the performance of the proposed method. The results obtained exhibit detection and accuracy rates which are, overall, superior to other techniques.

[1]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[2]  Sukadev Meher,et al.  Hierarchical background subtraction algorithm using Gabor filter , 2015, 2015 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT).

[3]  Qingshan Liu,et al.  Abnormal detection using interaction energy potentials , 2011, CVPR 2011.

[4]  S. Agarwal,et al.  Wavelet energy signature and GLCM features-based fingerprint anti-spoofing , 2008, 2008 International Conference on Wavelet Analysis and Pattern Recognition.

[5]  Robert C. Bolles,et al.  Generalizing Epipolar-Plane Image Analysis on the spatiotemporal surface , 2004, International Journal of Computer Vision.

[6]  Jia Guo,et al.  The Scheme of Detecting Encoded Malicious Web Pages Based on Information Entropy , 2016, 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS).

[7]  Alessio Del Bue,et al.  Optimizing interaction force for global anomaly detection in crowded scenes , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[8]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[9]  Qi Wang,et al.  Anomaly Detection in Crowd Scene via Online Learning , 2014, ICIMCS '14.

[10]  Sreela Sasi,et al.  Detection of Abnormal behavior in Dynamic Crowded Gatherings , 2013, 2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[11]  Lin Sun,et al.  Mobile Payment Anomaly Detection Mechanism Based on Information Entropy , 2014, 2014 Tenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[12]  Chong-Wah Ngo,et al.  Detection of gradual transitions through temporal slice analysis , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[13]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Chuan Zhou,et al.  Dynamic Textures Using Wavelet Analysis , 2006, Edutainment.

[15]  Edward H. Adelson,et al.  Analyzing and recognizing walking figures in XYT , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[17]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[18]  Sihem Kechida,et al.  A piecewise switched linear approach for traffic flow modeling , 2017, Int. J. Autom. Comput..

[19]  Liu Tong,et al.  The detecting of abnormal crowd activities based on motion vector , 2017 .

[20]  Qixiang Ye,et al.  Abnormal Behavior Detection via Sparse Reconstruction Analysis of Trajectory , 2011, 2011 Sixth International Conference on Image and Graphics.

[21]  Jun Xu,et al.  Abnormal behavior detection based on spatial-temporal features , 2013, 2013 International Conference on Machine Learning and Cybernetics.

[22]  M. Petrou,et al.  Person identification from spatio-temporal volumes , 2008, 2008 23rd International Conference Image and Vision Computing New Zealand.

[23]  Hong Duan,et al.  Agent-based simulation systems for emergency management , 2016, Int. J. Autom. Comput..

[24]  Jing Wang,et al.  STV-based video feature processing for action recognition , 2013, Signal Process..

[25]  Soraia Raupp Musse,et al.  Crowd Analysis Using Computer Vision Techniques , 2010, IEEE Signal Processing Magazine.

[26]  Robert C. Bolles,et al.  Epipolar-plane image analysis: An approach to determining structure from motion , 1987, International Journal of Computer Vision.

[27]  Hong Zhang,et al.  Texture based background subtraction , 2008, 2008 International Conference on Information and Automation.

[28]  Jing Wang,et al.  An approach to detect crowd panic behavior using flow-based feature , 2016, 2016 22nd International Conference on Automation and Computing (ICAC).

[29]  Bipan Tudu,et al.  Study on the potential of combined GLCM features towards medicinal plant classification , 2016, 2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC).

[30]  Christophe Rosenberger,et al.  Abnormal events detection based on spatio-temporal co-occurences , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Remco C. Veltkamp,et al.  Hands-on: deformable pose and motion models for spatiotemporal localization of fine-grained dyadic interactions , 2018, EURASIP J. Image Video Process..

[32]  Anupam Agrawal,et al.  Video Summary Based on F-Sift, Tamura Textural and Middle Level Semantic Feature , 2016 .

[33]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[34]  Gerald Kühne,et al.  Motion-based segmentation and contour-based classification of video objects , 2001, MULTIMEDIA '01.

[35]  Mubarak Shah,et al.  Identifying Behaviors in Crowd Scenes Using Stability Analysis for Dynamical Systems , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  He Kai,et al.  Study on denoising of fractal signal based on Shannon entropy , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[37]  Qian-Qian Wu,et al.  Study of Human Action Recognition Based on Improved Spatio-temporal Features , 2014, Int. J. Autom. Comput..

[38]  Christophe Rosenberger,et al.  Abnormal events detection based on spatio-temporal co-occurences , 2009, CVPR.

[39]  Christian Bauckhage,et al.  Loveparade 2010: Automatic video analysis of a crowd disaster , 2012, Comput. Vis. Image Underst..