A Context Model and Reasoning System to improve object tracking in complex scenarios

Tracking algorithms in computer vision usually fail when dealing with complex scenarios. This paper presents an extension of a general tracking system that uses context knowledge to solve tracking issues. The context layer represents knowledge about the context of the analyzed scenario and applies rules to reason with it, in order to assess the general tracking layer at different stages and enhance tracking results. The context knowledge representation and the reasoning methods are general and can be easily adapted to different scenarios. The experimentation results show that the performance of the tracking system is considerably improved, while the efficiency requirements that are mandatory in real-time systems are satisfied.

[1]  Pong C. Yuen,et al.  Automatic Acquisition of Context Models and its Application to Video Surveillance , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[2]  Gary Riley.  CLIPS: An expert system building tool , 1991 .

[3]  Patrick Brézillon,et al.  Context in problem solving: a survey , 1999, The Knowledge Engineering Review.

[4]  Arthur V. Forman,et al.  Contextual Analysis Of Tactical Scenes , 1984, Other Conferences.

[5]  Tim J. Ellis,et al.  Augmented tracking with incomplete observation and probabilistic reasoning , 2006, Image Vis. Comput..

[6]  Antonio Torralba,et al.  Context-based vision system for place and object recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Ana M. Sánchez,et al.  Video tracking improvement using context-based information , 2007, 2007 10th International Conference on Information Fusion.

[8]  Ajith Abraham,et al.  Computational Intelligence in Multimedia Processing: Recent Advances , 2008 .

[9]  Godfried T. Toussaint,et al.  The use of context in pattern recognition , 1978, Pattern Recognit..

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

[11]  Anind K. Dey,et al.  Understanding and Using Context , 2001, Personal and Ubiquitous Computing.

[12]  Miguel A. Patricio,et al.  Computational Intelligence in Visual Sensor Networks: Improving Video Processing Systems , 2008 .

[13]  Ramakant Nevatia,et al.  Tracking multiple humans in complex situations , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  M. Desvignes,et al.  A tool for studying context in Image sequences , 1989 .

[15]  W.Y. Kan,et al.  A generalization of the PDA target tracking algorithm using hypothesis clustering , 1996, Conference Record of The Thirtieth Asilomar Conference on Signals, Systems and Computers.

[16]  Miguel A. Patricio,et al.  Solving video-association problem with explicit evaluation of hypothesis using EDAs , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[17]  Juan A. Besada,et al.  Fuzzy approach for data association in image tracking , 2003 .

[18]  Trevor Darrell,et al.  Contextual recognition of head gestures , 2005, ICMI '05.