An advanced Bayesian model for the visual tracking of multiple interacting objects

Del, Jaureguizar Fernando, García, García Narciso

Description

Visual tracking of multiple objects is a key component of many visual-based systems. While there are reliable algorithms for tracking a single object in constrained scenarios, the object tracking is still a challenge in uncontrolled situations involving multiple interacting objects that have a complex dynamics. In this article, a novel Bayesian model for tracking multiple interacting objects in unrestricted situations is proposed. This is accomplished by means of an advanced object dynamic model that predicts possible interactive behaviors, which in turn depend on the inference of potential events of object occlusion. The proposed tracking model can also handle false and missing detections that are typical from visual object detectors operating in uncontrolled scenarios. On the other hand, a Rao-Blackwellization technique has been used to improve the accuracy of the estimated object trajectories, which is a fundamental aspect in the tracking of multiple objects due to its high dimensionality. Excellent results have been obtained using a publicly available database, proving the efficiency of the proposed approach.

Sujets

• Particle filter
• Rao?Blackwell theorem
• Correspondence problem

Informations

• Publié par: biomed
• Publié le: 01 janvier 2011
• Nombre de lectures: 9
• Langue: English
• Poids de l'ouvrage: 1 Mo

Extrait

del Blancoet al.EURASIP Journal on Advances in Signal Processing2011,2011:130 http://asp.eurasipjournals.com/content/2011/1/130

R E S E A R C HOpen Access An advanced Bayesian model for the visual tracking of multiple interacting objects * Carlos R del Blanco , Fernando Jaureguizar and Narciso García

Abstract Visual tracking of multiple objects is a key component of many visualbased systems. While there are reliable algorithms for tracking a single object in constrained scenarios, the object tracking is still a challenge in uncontrolled situations involving multiple interacting objects that have a complex dynamics. In this article, a novel Bayesian model for tracking multiple interacting objects in unrestricted situations is proposed. This is accomplished by means of an advanced object dynamic model that predicts possible interactive behaviors, which in turn depend on the inference of potential events of object occlusion. The proposed tracking model can also handle false and missing detections that are typical from visual object detectors operating in uncontrolled scenarios. On the other hand, a RaoBlackwellization technique has been used to improve the accuracy of the estimated object trajectories, which is a fundamental aspect in the tracking of multiple objects due to its high dimensionality. Excellent results have been obtained using a publicly available database, proving the efficiency of the proposed approach. Keywords:visual tracking, multiple objects, interacting model, particle filter, RaoBlackwellization, data association

1 Introduction Visual object tracking is a fundamental part in many videobased systems such as vehicle navigation, traffic monitoring, humancomputer interaction, motionbased recognition, security and surveillance, etc. While there exist reliable algorithms for the tracking of a single object in constrained scenarios, the object tracking is still a challenge in uncontrolled situations involving multiple objects with complex dynamics. The main pro blem is that object detectors produce a set of unlabeled and unordered detections, whose correspondence with the tracked objects is unknown. The estimation of this correspondence, called the data association problem, is of paramount importance for the proper estimation of the object trajectories. In addition, visual object detec tors can produce false and missing detections as conse quence of object appearance changes, illumination variations, occlusions, and scene structures similar to the objects of interest (also called clutter). This fact makes more complex the estimation of the true corre spondence between detections and objects. Another important issue related to the data association is the

* Correspondence: [e-mail] Escuela Técnica Superior de Ingenieros de Telecomunicación, Universidad Politécnica de Madrid, Madrid, 28040, Spain

computational cost, since it grows exponentially with the number of objects. To alleviate the data association problem, the tracking also relies on the prior knowledge about the object dynamics, which constrains the feasible associations between detections and objects. Nonetheless, the model ing of the object dynamics can be a very difficult task, especially in situations in which the objects undergo complex interactions. Besides, the estimation of the object trajectories can be quite inaccurate in situations involving many objects due to the high dimensionality of the resulting tracking problem, which is called the curse of dimensionality [1]. In this article, an efficient Bayesian tracking frame work for multiple interacting objects in complex situa tions is proposed. Complex object interactions are simulated by means of a novel dynamic model that uses potential events of object occlusions to predict different object behaviors. This interacting dynamic model allows to appropriately estimate a set of data association hypotheses that are used for the estimation of the object trajectories. On the other hand, a RaoBlackwellization strategy [2] has been used to derive an approximation of the posterior distribution over the object trajectories,

© 2011 del Blanco et al; licensee Springer. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.