Beyond particle flow: Bag of Trajectory Graphs for dense crowd event recognition

In this paper, a novel crowd behavior representation, Bag of Trajectory Graphs (BoTG), is presented for dense crowd event recognition. To overcome huge loss of crowd structure and variability of motion in previous particle flow based methods, we design group-level representation beyond particle flow. From the observation that crowd particles are composed of atomic subgroups corresponding to informative behavior patterns, particle trajectories which simulate motion of individuals will be clustered to form groups at the first step. Then we connect nodes in each group as a trajectory graph and discover informative features to depict the graphs. A clip of crowd event can be further described by Bag of Trajectory Graphs (BoTG)-occurrences of behavior patterns, which provides critical clues for categorizing specific crowd event and detecting abnormality. The experimental results of abnormality detection and event recognition on public datasets demonstrate the effectiveness of our proposed BoTG on characterizing the group behaviors in dense crowd.

[1]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[3]  Ehud Rivlin,et al.  Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Mubarak Shah,et al.  Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories , 2011, 2011 International Conference on Computer Vision.

[5]  Jin Tang,et al.  A graph and PNN-based approach to image classification , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[6]  Chabane Djeraba,et al.  Real-time crowd motion analysis , 2008, 2008 19th International Conference on Pattern Recognition.

[7]  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.

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

[9]  Louis Kratz,et al.  Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models , 2009, CVPR.

[10]  Junsong Yuan,et al.  Optimal spatio-temporal path discovery for video event detection , 2011, CVPR 2011.

[11]  Mubarak Shah,et al.  Floor Fields for Tracking in High Density Crowd Scenes , 2008, ECCV.

[12]  Luc Van Gool,et al.  You'll never walk alone: Modeling social behavior for multi-target tracking , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[14]  Qingming Huang,et al.  Abnormal crowd behavior detection based on social attribute-aware force model , 2012, 2012 19th IEEE International Conference on Image Processing.

[15]  Luc Van Gool,et al.  What's going on? Discovering spatio-temporal dependencies in dynamic scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Robert T. Collins,et al.  Automatically detecting the small group structure of a crowd , 2009, 2009 Workshop on Applications of Computer Vision (WACV).

[17]  Mubarak Shah,et al.  Learning object motion patterns for anomaly detection and improved object detection , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[19]  Qi Tian,et al.  Group Activity Recognition by Gaussian Processes Estimation , 2010, 2010 20th International Conference on Pattern Recognition.

[20]  Junsong Yuan,et al.  Sparse reconstruction cost for abnormal event detection , 2011, CVPR 2011.

[21]  Shaogang Gong,et al.  A Markov Clustering Topic Model for mining behaviour in video , 2009, 2009 IEEE 12th International Conference on Computer Vision.