Learning Video Manifold for Segmenting Crowd Events and Abnormality Detection

This paper addresses the problem of analyzing video events in crowded scenes. A novel manifold learning method is proposed to achieve visualization and modeling of video events in a low dimensional space. In the proposed approach, a video is considered as a trajectory of frames in a low-dimensional space. This low-dimensional representation of a video preserves the spatio-temporal property of a video as well as the characteristic of the video. Different tasks of video content analysis such as visualization, video event segmentation and abnormality detection are achieved by analyzing these video trajectories based on the Hausdorff distance similarity measure. We evaluate our proposed method on the state-of-the-art public data-sets containing different crowd events. Qualitative and quantitative results show the promising performance of the proposed method.

[1]  Kap Luk Chan,et al.  Face recognition based on discriminative manifold learning , 2004, ICPR 2004.

[2]  Liang Wang,et al.  Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition , 2007, IEEE Transactions on Image Processing.

[3]  Liang Wang,et al.  Analyzing Human Movements from Silhouettes Using Manifold Learning , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[4]  Ernesto Andrade,et al.  Simulation of Crowd Problems for Computer Vision , 2005 .

[5]  Robert B. Fisher,et al.  Modelling Crowd Scenes for Event Detection , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[6]  Tieniu Tan,et al.  A system for learning statistical motion patterns , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[8]  Robert B. Fisher,et al.  Performance Analysis of Event Detection Models in Crowded Scenes , 2006 .

[9]  Liang Lin,et al.  An empirical study of facial components classification by integrating dimensionality reduction and clustering , 2008, 2008 19th International Conference on Pattern Recognition.

[10]  Robert B. Fisher,et al.  Detection of Emergency Events in Crowded Scenes , 2006 .

[11]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[12]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, ICPR 2004.

[13]  David C. Hogg,et al.  Learning the distribution of object trajectories for event recognition , 1996, Image Vis. Comput..

[14]  Thomas Brox,et al.  High Accuracy Optical Flow Estimation Based on a Theory for Warping , 2004, ECCV.

[15]  W. Eric L. Grimson,et al.  Learning Semantic Scene Models by Trajectory Analysis , 2006, ECCV.

[16]  Mubarak Shah,et al.  Detecting global motion patterns in complex videos , 2008, 2008 19th International Conference on Pattern Recognition.

[17]  A. Elgammal,et al.  Inferring 3D body pose from silhouettes using activity manifold learning , 2004, CVPR 2004.

[18]  M. Turk,et al.  Probabilistic expression analysis on manifolds , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[19]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[21]  Mubarak Shah,et al.  Learning motion patterns in crowded scenes using motion flow field , 2008, 2008 19th International Conference on Pattern Recognition.

[22]  Robert Pless,et al.  Image spaces and video trajectories: using Isomap to explore video sequences , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[23]  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.

[24]  Wen Gao,et al.  Manifold-Manifold Distance with application to face recognition based on image set , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Andrea Cavallaro,et al.  Video event segmentation and visualisation in non-linear subspace , 2009, Pattern Recognit. Lett..

[26]  F. Bremond,et al.  Crowd event recognition using HOG tracker , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.