Dynamic Attribute Package: Crowd Behavior Recognition in Complex Scene

Crowd behavior recognition under complex surveillance scenarios is a fundamental and important problem in crowd management application. In this paper, a comprehensive and specific overall-level dynamic attribute package is proposed by considering local pattern-related motion and group-level motion together to represent crowd movement. Curl and divergence map of normalized average motion vector field act as local pattern-related motion, which represents physical movement tendency of each particle. Group-level motion explores crowd interaction of inter-/intra-group, which focus on depicting crowd’s social dynamic property. The complementary characteristic of two motion representation in different level is analyzed and verified. Single frames in video clips and the corresponding dynamic attribute packages are sent into two-branch structured ConvNet, which can extract more discriminative spatial-temporal feature for behavior recognition. Experiment results conducted on CUHK dataset show that the proposed crowd behavior recognition framework outperforms than existing approaches and obtains the state-of-art performance.

[1]  Cordelia Schmid,et al.  EpicFlow: Edge-preserving interpolation of correspondences for optical flow , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Xiaogang Wang,et al.  Deeply learned attributes for crowded scene understanding , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  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.

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

[5]  Xiaogang Wang,et al.  Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Shuang Wu,et al.  Crowd Behavior Analysis via Curl and Divergence of Motion Trajectories , 2017, International Journal of Computer Vision.

[7]  Takeo Kanade,et al.  Tracking in unstructured crowded scenes , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[8]  Simon C. K. Shiu,et al.  Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary , 2013, Pattern Recognit..

[9]  Xiaogang Wang,et al.  Scene-Independent Group Profiling in Crowd , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Shuang Wu,et al.  Motion sketch based crowd video retrieval via motion structure coding , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[11]  Saad Ali.  Measuring Flow Complexity in Videos , 2013, 2013 IEEE International Conference on Computer Vision.

[12]  Jing Zhao,et al.  Crowd instability analysis using velocity-field based social force model , 2011, 2011 Visual Communications and Image Processing (VCIP).

[13]  Kate Saenko,et al.  Guest Editorial: Image and Language Understanding , 2017, International Journal of Computer Vision.

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

[15]  Ko Nishino,et al.  Tracking Pedestrians Using Local Spatio-Temporal Motion Patterns in Extremely Crowded Scenes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[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]  Junsong Yuan,et al.  Abnormal event detection in crowded scenes using sparse representation , 2013, Pattern Recognit..

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

[19]  Shuang Wu,et al.  Bilinear dynamics for crowd video analysis , 2017, J. Vis. Commun. Image Represent..

[20]  Bingbing Ni,et al.  Crowded Scene Analysis: A Survey , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  Hua Yang,et al.  The Large-Scale Crowd Behavior Perception Based on Spatio-Temporal Viscous Fluid Field , 2013, IEEE Transactions on Information Forensics and Security.

[23]  Xiaogang Wang,et al.  Learning Scene-Independent Group Descriptors for Crowd Understanding , 2017, IEEE Transactions on Circuits and Systems for Video Technology.