Video tracking improvement using context-based information

Video target tracking is a complex task, specially when the tracking system is expected to work well in different scenarios. For this reason, this paper proposes an architecture based on a two layer image-processing modules: general tracking layer (GTL) and context layer (CL). GTL describes a generic multipurpose tracking process for video surveillance systems. CL is designed as a symbolic reasoning system that manages the symbolic interface data between GTL modules in order to assess a specific situation and take the appropriate decision. CL intervenes at three different stages of the tracking process, these are initialization, association and update. Our architecture has been tested in two different scenarios to show the advantages in improved performance and output continuity.

[1]  Massimo Piccardi,et al.  Comparison between Genetic Algorithms and Baum- Welch algorithm for the adjustment of HMM to Classify Human Activities 1 , 2005 .

[2]  Jesús García,et al.  A Multitarget Tracking Video System Based on Fuzzy and Neuro-Fuzzy Techniques , 2005, EURASIP J. Adv. Signal Process..

[3]  Hideo Saito,et al.  Tracking Soccer Player Using Multiple Views , 2002, MVA.

[4]  Derek R. Magee,et al.  Computer vision based analysis in sport environments , 2009, Computer Vision and Image Understanding.

[5]  Miguel A. Patricio,et al.  Improving the Segmentation Stage of a Pedestrian Tracking Video-Based System by Means of Evolution Strategies , 2006, EvoWorkshops.

[6]  R. Cucchiara.  Multimedia surveillance systems , 2005, VSSN@MM.

[7]  Jean-François Delaigle,et al.  Real-time high-level video understanding using data warehouse , 2006, Electronic Imaging.

[8]  Kuntal Sengupta,et al.  Co-operative Multi-target Tracking and Classification , 2004, ECCV.

[9]  Miguel A. Patricio,et al.  Fusion of Surveillance Information for Visual Sensor Networks , 2006, 2006 9th International Conference on Information Fusion.

[10]  Baoxin Li,et al.  Rao-Blackwellised particle filter for tracking with application in visual surveillance , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[11]  A. Farina,et al.  Knowledge-based system for multi-target tracking in a littoral environment , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[12]  Gian Luca Foresti,et al.  Special issue on video communications, processing, and understanding for third generation surveillance systems , 2001 .

[13]  Miguel A. Patricio,et al.  Multi-Agent Framework in Visual Sensor Networks , 2007, EURASIP J. Adv. Signal Process..

[14]  Roger D. Boyle,et al.  Tracking multiple sports players through occlusion, congestion and scale , 2001, BMVC.