%0 Conference Proceedings
%T User Identification and Object Recognition in Clutter Scenes Based on RGB-Depth Analysis
%A Albert Clapes
%A Miguel Reyes
%A Sergio Escalera
%B 7th Conference on Articulated Motion and Deformable Objects
%D 2012
%V 7378
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-31566-4
%F Albert Clapes2012
%O HUPBA;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2010), last updated on Thu, 18 Jan 2018 11:42:50 +0100
%X We propose an automatic system for user identification and object recognition based on multi-modal RGB-Depth data analysis. We model a RGBD environment learning a pixel-based background Gaussian distribution. Then, user and object candidate regions are detected and recognized online using robust statistical approaches over RGBD descriptions. Finally, the system saves the historic of user-object assignments, being specially useful for surveillance scenarios. The system has been evaluated on a novel data set containing different indoor/outdoor scenarios, objects, and users, showing accurate recognition and better performance than standard state-of-the-art approaches.
%U http://refbase.cvc.uab.es/files/CRE2012.pdf
%U http://dx.doi.org/10.1007/978-3-642-31567-1_1
%P 1-11