Color-Based Object Tracking in Multi-camera Environments

Nummiaro, Katja; Koller-Meier, Esther; Svoboda, Tomáš; Roth, Daniel; Gool, Luc J. Van

doi:10.1007/978-3-540-45243-0_75

Cited by 89 publications

(62 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the observation process is to match the color histogram in a candidate region, a particle, with a pre-learned reference model, where the Bhattacharyya similarity coefficient is computed to measure the distance. The effectiveness of this model has been shown previously [11,12,4] and is confirmed by this work. In all the experiments, we manually initialize the regions of targets of interest at the first frame of each camera and learn the reference color models.…”

Section: Resultssupporting

confidence: 88%

“…Our approach is superior to the best view selection strategy proposed in [4,5] in that the full information at all the views is taken into consideration during tracking. Even a view in which the target is completely occluded "contributes" to the tracking results by propagating uniformly distributed belief to other views.…”

Section: The Monte Carlo Implementationmentioning

confidence: 93%

“…Particle filters are popular in multi-view tracking [4,5]. Both cited approaches are based on the best-view-selection strategy: the target states are estimated using mainly those views that contain the most likely information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-view Object Tracking Using Sequential Belief Propagation

Piater

2006

Computer Vision – ACCV 2006

View full text Add to dashboard Cite

Abstract. Multiple cameras and collaboration between them make possible the integration of information available from multiple views and reduce the uncertainty due to occlusions. This paper presents a novel method for integrating and tracking multi-view observations using bidirectional belief propagation. The method is based on a fully connected graphical model where target states at different views are represented as different but correlated random variables, and image observations at a given view are only associated with the target states at the same view. The tracking processes at different views collaborate with each other by exchanging information using a message passing scheme, which largely avoids propagating wrong information. An efficient sequential belief propagation algorithm is adopted to perform the collaboration and to infer the multi-view target states. We demonstrate the effectiveness of our method on video-surveillance sequences.

show abstract

Section: Resultssupporting

confidence: 88%

Section: The Monte Carlo Implementationmentioning

confidence: 93%

See 1 more Smart Citation

Multi-view Object Tracking Using Sequential Belief Propagation

Piater

2006

Computer Vision – ACCV 2006

View full text Add to dashboard Cite

show abstract

“…After the work of [3], in which particle filters were introduced for the first time in computer vision, in the context of active contours tracking, Monte-Carlo methods have taken the lead in the literature. Pérez et al [4], on the one hand, and Nummiaro et al [5], on the other hand, have proposed the first particle filter trackers based on color histograms, in the context of face tracking. It has proven to be particularly robust, e.g.…”

Section: Related Workmentioning

confidence: 99%

Multiple Target Tracking with Motion Priors

Madrigal

Rivera

Hayet

2011

Advances in Soft Computing

View full text Add to dashboard Cite

Abstract. This paper presents a particle filter-based approach for multiple target tracking in video streams in single static cameras settings. We aim in particular to manage mid-dense crowds situations, where, although tracking is possible, it is made complicated by the presence of frequent occlusions among targets and with scene clutter. Moreover, the appearance of targets is sometimes very similar, which makes standard trackers often switch their target identity. Our contribution is two-fold: (1) we first propose an estimation scheme for motion priors in the camera field of view, that integrates sparse optical flow data and regularizes the corresponding discrete distribution fields on velocity directions and magnitudes; (2) we use these motion priors in a hybrid motion model for a particle filter tracker. Through several results on video-surveillance datasets, we show the pertinence of this approach.

show abstract

“…The main bottleneck of developing object tracking algorithms is that a camera may have insufficient target information caused by object occlusion and by the indistinct nature of the object in front of cluttered backgrounds. Recent studies of object tracking methods using multiple cameras [1][2][3][4][5] rely on the concept of collaborative tracking of a moving target to overcome these difficulties.…”

Section: Introductionmentioning

confidence: 99%