eprintid: 7270 rev_number: 22 eprint_status: archive userid: 314 dir: disk0/00/00/72/70 datestamp: 2011-05-27 11:43:59 lastmod: 2016-04-20 16:27:08 status_changed: 2011-05-27 11:43:59 type: conference_item metadata_visibility: show item_issues_count: 0 creators_name: Blanco Adán, Carlos Roberto del creators_name: Jaureguizar Núñez, Fernando creators_name: García Santos, Narciso creators_id: cda@gti.ssr.upm.es creators_id: fjn@gti.ssr.upm.es creators_id: narciso@gti.ssr.upm.es title: Visual tracking of multiple interacting objects through Rao-Blackwellized data association particle filtering publisher: IEEE rights: by-nc-nd ispublished: pub subjects: telecomunicaciones subjects: robotica subjects: informatica full_text_status: public pres_type: paper keywords: Atmospheric measurements , Clutter , Detectors , Particle filters , Particle measurements , Position measurement , Radar tracking abstract: A multiple object visual tracking framework is presented, which is able to manage complex object interactions, missing detections and clutter. The main contribution is the ability to deal with complex situations in which the interacting objects can change their dynamics while they are occluded. This is achieved by explicitly estimating putative locations of the occluded objects. The tracking is modeled by a Rao-Blackwellized Data Association Particle Filter (RBDAPF), which has a tractable substructure that allows to analytically compute the object positions, while the object-measurement associations are approximated by Particle Filtering. Besides improving the accuracy, this filter decomposition reduces the computational cost, since the complexity with the number of objects becomes linear instead of exponential. The Particle Filter efficiently manages the measurements from visible and occluded objects, the clutter, and missing measurements to estimate the correct data associations that lead to a robust tracking. Experimental results on surveillance videos show that the proposed RBDAPF framework is able to track multiple interacting objects in complex situations. date_type: published date: 2010-12-03 pages: 4 event_title: 17th IEEE International Conference on Image Processing (ICIP) event_location: Hong Kong event_dates: 26-29 de Septiembre del 2010 event_type: conference institution: Telecomunicacion department: Senales refereed: TRUE isbn: 978-1-4244-7992-4 book_title: 17th IEEE International Conference on Image Processing (ICIP) official_url: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5653411 citation: Blanco Adán, Carlos Roberto del and Jaureguizar Núñez, Fernando and García Santos, Narciso (2010). Visual tracking of multiple interacting objects through Rao-Blackwellized data association particle filtering. In: "17th IEEE International Conference on Image Processing (ICIP)", 26-29 de Septiembre del 2010, Hong Kong. ISBN 978-1-4244-7992-4. document_url: https://oa.upm.es/7270/1/2010_Visual_tracking_of_multiple_interacting_objects_through_Rao-Blackwellized_data_association_particle_filtering.pdf