Observatorio de I+D+i UPM

Descripción
Object tracking through particle filtering has been widely addressed in recent years. However, most works assume a constant number of objects or utilize an external detector that monitors the entry or exit of objects in the scene. In this work, a novel tracking method based on particle filtering that is able to automatically track a variable number of objects is presented. As opposed to classical prior data assignment approaches, adaptation of tracks to the measurements is managed globally. Additionally, the designed particle filter is able to generate hypotheses on the presence of new objects in the scene, and to confirm or dismiss them by gradually adapting to the global observation. The method is especially suited for environments where traditional object detectors render noisy measurements and frequent artifacts, such as that given by a camera mounted on a vehicle, where it is proven to yield excellent results.
Internacional	Si
Nombre congreso	IEEE International Conference on Image Processing
Tipo de participación	960
Lugar del congreso	Hong Kong, China
Revisores	Si
ISBN o ISSN	1522-4880
DOI	10.1109/ICIP.2010.5651632
Fecha inicio congreso	26/09/2010
Fecha fin congreso	29/09/2010
Desde la página	49
Hasta la página	52
Título de las actas	Multiple object tracking using an automatic variable-dimension particle filter

Esta actividad pertenece a memorias de investigación

• Autor: Jon Arróspide Laborda (UPM)
• Autor: Luis Salgado Alvarez de Sotomayor (UPM)
• Autor: Marcos Nieto Doncel (Vicomtech-IK4, Research Alliance)

• Creador: Grupo de Investigación: Grupo de Tratamiento de Imágenes (GTI)
• Departamento: Señales, Sistemas y Radiocomunicaciones