Event Modeling and Recognition Using Markov Logic Networks

We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited to overcome them. The knowledge is represented as first-order logic production rules with associated weights to indicate their confidence. These rules are used in combination with a relaxed deduction algorithm to construct a network of grounded atoms, the Markov Logic Network. The network is used to perform probabilistic inference for input queries about events of interest. The system's performance is demonstrated on a number of videos from a parking lot domain that contains complex interactions of people and vehicles.

[1]  Matthew Richardson,et al.  The Alchemy System for Statistical Relational AI: User Manual , 2007 .

[2]  Ben Taskar,et al.  Introduction to statistical relational learning , 2007 .

[3]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Matthew Richardson,et al.  Markov logic networks , 2006, Machine Learning.

[5]  Ramakant Nevatia,et al.  Hierarchical Language-based Representation of Events in Video Streams , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[6]  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).

[7]  Henry A. Kautz,et al.  Location-Based Activity Recognition using Relational Markov Networks , 2005, IJCAI.

[8]  Sebastian Thrun,et al.  Recognizing Activities with Multiple Cues , 2007, Workshop on Human Motion.

[9]  S. Baum,et al.  Intro , 2003, Science.

[10]  Pedro M. Domingos,et al.  Entity Resolution with Markov Logic , 2006, Sixth International Conference on Data Mining (ICDM'06).

[11]  Larry S. Davis,et al.  Bilattice-based Logical Reasoning for Human Detection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Henry A. Kautz,et al.  Sensor-Based Understanding of Daily Life via Large-Scale Use of Common Sense , 2006, AAAI.

[13]  Monique Thonnat,et al.  Activity Recognition from Video Sequences using Declarative Models , 2000, ECAI.

[14]  Jack Minker,et al.  Disjunctive Logic Programming: A Survey and Assessment , 2002, Computational Logic: Logic Programming and Beyond.

[15]  Pedro M. Domingos,et al.  Memory-Efficient Inference in Relational Domains , 2006, AAAI.

[16]  Larry S. Davis,et al.  Multivalued Default Logic for Identity Maintenance in Visual Surveillance , 2006, ECCV.

[17]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Ulrich Berger,et al.  Computational Logic , 2001, NATO ASI Series.