We present an approach to tracking multiple human subjects within a camera network. A particle filter frame-work is used in which we combine foreground-background subtraction with a novel approach to texture learning and likelihood computation based on an ellipsoid model. As there are inevitable problems with multiple subjects due to occlusion and crossing, we include a robust method to suppress distraction between subjects. To achieve real-time performance, we have also developed our code on a graphics processing unit to achieve a 10-fold reduction in processing time with an approximate frame rate of 10 frames per second.
|Title of host publication||Proceedings of the International Conference on Computer Vision Theory and Applications 2012|
|Publication status||Published - Feb 2012|
|Event||International Conference on Computer Vision Theory and Applications 2012 - Rome, Italy|
Duration: 24 Feb 2012 → 26 Feb 2012
|Conference||International Conference on Computer Vision Theory and Applications 2012|
|Abbreviated title||VISAPP 2012|
|Period||24/02/12 → 26/02/12|