Analyzing crowd behavior in naturalistic conditions: Identifying sources and sinks and characterizing main flows

Pedestrians, in videos taken from fixed cameras, tend to appear and disappear at precise locations such as doors, gateways or edges of the scene: we refer to locations where pedestrians appear as sources (potential origins) and the locations where they disappear as sinks (potential destinations). The detection of these points and the characterization of the flows connecting them represent a typical preliminary step in most pedestrian studies and it can be supported by computer vision approaches. In this paper we propose an algorithm in which a scene is overlaid by a grid of particles initializing a dynamical system defined by optical flow, a high level global motion information. Time integration of the dynamical system produces short particle trajectories (tracklets), representing dense but short motion patterns in segments of the scene; tracklets are then extended into longer tracks that are grouped using an unsupervised clustering algorithm, where the similarity is measured by the Longest Common Subsequence. The analysis of these clusters supports the identification of sources and sinks related to a single video segment. Local segment information is finally combined to achieve a global set of traces identifying sources and sinks, and characterizing the flow of pedestrians connecting them. The paper presents the defined technique and it discusses its application in a real-world scenario.

[1]  Xiaogang Wang,et al.  Random field topic model for semantic region analysis in crowded scenes from tracklets , 2011, CVPR 2011.

[2]  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.

[3]  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.

[4]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[5]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[6]  Seth J. Teller,et al.  Particle Video: Long-Range Motion Estimation Using Point Trajectories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  KriegelHans-Peter,et al.  Density-Based Clustering in Spatial Databases , 1998 .

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

[9]  Lorenza Manenti,et al.  Data Collection for Modeling and Simulation: Case Study at the University of Milan-Bicocca , 2012, ACRI.

[10]  James W. Davis,et al.  Learning Scene Entries and Exits Using Coherent Motion Regions , 2010, ISVC.

[11]  MatthewsIain,et al.  Lucas-Kanade 20 Years On , 2004 .

[12]  Dimitrios Gunopulos,et al.  Discovering similar multidimensional trajectories , 2002, Proceedings 18th International Conference on Data Engineering.

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

[14]  Martial Hebert,et al.  Trajectons: Action recognition through the motion analysis of tracked features , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[15]  Takahiro Okabe,et al.  Using individuality to track individuals: Clustering individual trajectories in crowds using local appearance and frequency trait , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  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).

[17]  James W. Davis,et al.  Learning Directed Intention-driven Activities using Co-Clustering , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[18]  Loong Fah Cheong,et al.  Activity recognition using dense long-duration trajectories , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[19]  Stefano Soatto,et al.  Tracklet Descriptors for Action Modeling and Video Analysis , 2010, ECCV.

[20]  Sebastiano Battiato,et al.  SIFT Features Tracking for Video Stabilization , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[21]  Afshin Dehghan,et al.  GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs , 2012, ECCV.

[22]  Christopher Joseph Pal,et al.  Activity recognition using the velocity histories of tracked keypoints , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[23]  Jintao Li,et al.  Hierarchical spatio-temporal context modeling for action recognition , 2009, CVPR.

[24]  Ramakant Nevatia,et al.  Tracking multiple humans in crowded environment , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

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

[26]  Ivan Laptev,et al.  On Space-Time Interest Points , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[27]  Yu-Chiang Frank Wang,et al.  Learning Dense Optical-Flow Trajectory Patterns for Video Object Extraction , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[28]  Armin Seyfried,et al.  Collecting pedestrian trajectories , 2013, Neurocomputing.

[29]  C. Hue,et al.  Posterior Cramer-Rao bounds for multi-target tracking , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[30]  Hans-Peter Kriegel,et al.  Density-Based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications , 1998, Data Mining and Knowledge Discovery.

[31]  Stefania Bandini,et al.  Towards an Integrated Approach to Crowd Analysis and Crowd Synthesis: a Case Study and First Results , 2013, Pattern Recognit. Lett..

[32]  Philipp Berens,et al.  The circular statistics toolbox for Matlab , 2009 .

[33]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Jae-Gil Lee,et al.  Trajectory clustering: a partition-and-group framework , 2007, SIGMOD '07.

[35]  Chris Stauffer,et al.  Estimating Tracking Sources and Sinks , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[36]  Jintao Li,et al.  Hierarchical spatio-temporal context modeling for action recognition , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Jitendra Malik,et al.  Object Segmentation by Long Term Analysis of Point Trajectories , 2010, ECCV.

[38]  Philipp Berens,et al.  CircStat: AMATLABToolbox for Circular Statistics , 2009, Journal of Statistical Software.

[39]  Tieniu Tan,et al.  Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scenes , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[40]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[41]  Anil M. Cheriyadat,et al.  Detecting Dominant Motions in Dense Crowds , 2008, IEEE Journal of Selected Topics in Signal Processing.

[42]  Stefania Bandini,et al.  Detecting Dominant Motion Flows and People Counting in High Density Crowds , 2014, J. WSCG.

[43]  Kiyoharu Aizawa,et al.  Detecting Dominant Motion Flows in Unstructured/Structured Crowd Scenes , 2010, 2010 20th International Conference on Pattern Recognition.

[44]  Konrad Schindler,et al.  Continuous Energy Minimization for Multitarget Tracking , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

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

[47]  Anil M. Cheriyadat,et al.  Automatically Determining Dominant Motions in Crowded Scenes by Clustering Partial Feature Trajectories , 2007, 2007 First ACM/IEEE International Conference on Distributed Smart Cameras.

[48]  Liu Yuncai,et al.  Analyzing motion patterns in crowded scenes via automatic tracklets clustering , 2013, China Communications.