Detecting anomalous human interactions using laser range-finders

We present a laser range-finder-based system for tracking people in an outdoor environment and detecting interactions between them. The system does not use identities of people for tracking. Observed tracks are automatically segmented into individual activities using an entropy-based measure (Jensen-Shannon divergence (Lin, J, 1991)). Two people situated close to each other throughout the duration of an activity represents an interaction. The observed activities are combined using a hierarchical clustering algorithm to generate a representative set. The frequency of occurrence of these activities is modeled by a Poisson distribution. During the monitoring phase, this model is used to compute the probability of observing the detected activities and interactions; an anomaly is flagged if this probability falls below a threshold. Experimental results from an outdoor courtyard environment are described where the system indicates anomalies when there is a sudden increase in the number of people in the environment or in the number of interactions. This detection occurs without giving the system any a priori concepts of space occupancy.

[1]  Aaron F. Bobick,et al.  Video surveillance of interactions , 1999, Proceedings Second IEEE Workshop on Visual Surveillance (VS'99) (Cat. No.98-89223).

[2]  Aaron F. Bobick,et al.  Action recognition using probabilistic parsing , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[3]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Wolfram Burgard,et al.  Learning motion patterns of persons for mobile service robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[5]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[6]  Ramakant Nevatia,et al.  Representation and optimal recognition of human activities , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  P. Bernaola-Galván,et al.  Compositional segmentation and long-range fractal correlations in DNA sequences. , 1996, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[8]  Henry A. Kautz,et al.  Inferring High-Level Behavior from Low-Level Sensors , 2003, UbiComp.

[9]  Alex Pentland,et al.  Statistical Modeling of Human Interactions , 1998, CVPR 1998.

[10]  Thomas Eiter,et al.  Where is ...? Learning and Utilizing Motion Patterns of Persons with Mobile Robots , 2003, IJCAI.

[11]  M. Matari,et al.  Modeling Human Interactions in Indoor Environments , 2004 .

[12]  Maja J. Mataric,et al.  General spatial features for analysis of multi-robot and human activities from raw position data , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Maja J. Mataric,et al.  A laser-based people tracker , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[14]  Alex Pentland,et al.  Graphical Models for Recognizing Human Interactions , 1998, NIPS.

[15]  Gaurav S. Sukhatme,et al.  Relaxation on a mesh: a formalism for generalized localization , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[16]  Ramakant Nevatia,et al.  Bayesian framework for video surveillance application , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[17]  Maja J. Mataric,et al.  Temporal occupancy grids: a method for classifying the spatio-temporal properties of the environment , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.