<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>13</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Alvaro Marcos</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Marta Marron</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Seguimiento de Múltiples Objetos en Espacios Inteligentes</style></title></titles><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">07/2009</style></date></pub-dates></dates><urls><related-urls><url><style face="normal" font="default" size="100%">https://geintra-uah.org/system/files/Seguimiento_de_Multiples_Objetos_en_Espacios_Inteligentes.pdf</style></url></related-urls></urls><publisher><style face="normal" font="default" size="100%">Department of Electronics</style></publisher><pub-location><style face="normal" font="default" size="100%">Alcalá de Henares</style></pub-location><pages><style face="normal" font="default" size="100%">194</style></pages><language><style face="normal" font="default" size="100%">English</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This thesis goes through two multiple object tracking methods in intelligent spaces. The observation model is based in a ring of fully calibrated and synchronized cameras, strategically placed in the environment to extract all the information and interact with it. This work presents two ways of using that information. The first one is to obtain the position, trajectories and speed of the present objects in the scene ([Marr&amp;oacute;n08]), together with the identity of a robot, all in two dimensions. The second one is to get a three dimensional volume reconstruction of those objects.&lt;br /&gt;
Also, tracking with those two variants is done by using probabilistic techniques, in order to increase the robustness of the system against perturbations.&lt;br /&gt;
Each entity is defined individually from the tracking data. This way, a robot can be spotted from the rest of the elements, by using its odometry. The reliability and robustness of the proposal presented is finally demonstrated in this thesis, with different tests from real data.&lt;/p&gt;</style></abstract><work-type><style face="normal" font="default" size="100%">Master</style></work-type><custom1><style face="normal" font="default" size="100%">Master Degree in Advanced Electronic Systems</style></custom1><custom2><style face="normal" font="default" size="100%">Escuela Politecnica Superior</style></custom2><custom3><style face="normal" font="default" size="100%">University of Alcala</style></custom3><num-vols><style face="normal" font="default" size="100%">1 vol.</style></num-vols></record></records></xml>