Bayesian Visual Surveillance, a Model for Detecting and Tracking a variable number of moving objects

Blanco Adán, Carlos Roberto del and Jaureguizar Núñez, Fernando and García Santos, Narciso (2011). Bayesian Visual Surveillance, a Model for Detecting and Tracking a variable number of moving objects. In: "IEEE International Conference on Image Processing 2011", 13-14 de Enero del 2011, Bruselas, Bélgica. ISBN 978-1-4577-1304-0.

Description

Title: Bayesian Visual Surveillance, a Model for Detecting and Tracking a variable number of moving objects
Author/s:
  • Blanco Adán, Carlos Roberto del
  • Jaureguizar Núñez, Fernando
  • García Santos, Narciso
Item Type: Presentation at Congress or Conference (Article)
Event Title: IEEE International Conference on Image Processing 2011
Event Dates: 13-14 de Enero del 2011
Event Location: Bruselas, Bélgica
Title of Book: IEEE International Conference on Image Processing 2011
Date: 11 September 2011
ISBN: 978-1-4577-1304-0
Subjects:
Freetext Keywords: Split detections, merged detections, moving regions, multiple object tracking, variable number of objects.
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: None

Full text

[thumbnail of Bayesian Visual Surveillance, a Model for Detecting and Tracking a variable number of moving objects]
Preview
PDF (Bayesian Visual Surveillance, a Model for Detecting and Tracking a variable number of moving objects) - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

An automatic detection and tracking framework for visual surveillance is proposed, which is able to handle a variable number of moving objects. Video object detectors generate an unordered set of noisy, false, missing, split, and merged measurements that make extremely complex the tracking task. Especially challenging are split detections (one object is split into several measurements) and merged detections (several objects are merged into one detection). Few approaches address this problem directly, and the existing ones use heuristics methods, or assume a known number of objects, or are not suitable for on-line applications. In this paper, a Bayesian Visual Surveillance Model is proposed that is able to manage undesirable measurements. Particularly, split and merged measurements are explicitly modeled by stochastic processes. Inference is accurately performed through a particle filtering approach that combines ancestral and MCMC sampling. Experimental results have shown a high performance of the proposed approach in real situations.

More information

Item ID: 10365
DC Identifier: https://oa.upm.es/10365/
OAI Identifier: oai:oa.upm.es:10365
Official URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arn...
Deposited by: Doctor Carlos Roberto del Blanco Adán
Deposited on: 17 Feb 2012 09:01
Last Modified: 20 Apr 2016 18:34
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM