An adaptive color-based particle filter

Nummiaro, Katja; Koller-Meier, Esther; Gool, Luc J. Van

doi:10.1016/s0262-8856(02)00129-4

Cited by 1,109 publications

(818 citation statements)

References 12 publications

Supporting

Mentioning

813

Contrasting

Unclassified

Order By: Relevance

“…In this section, we report the performance of the proposed tracker over three diverse and challenging datasets and compare it with that of three tracking algorithms representative of the state of the art for various tracking approaches: the mean-shift tracker (MS), representative of appearance-based trackers [16]; the connected-component mean-shift with particle filter tracker (CCMSPF), representative of particle filters [14,17]; and the multiple-object tracker using k-shortest paths optimization (KSP), representative of trackers optimizing data association over multiple frames [2]. At the time of conducting these experiments, we did not have access to other part-based trackers and only a qualitative comparison is addressed in this section.…”

Section: Resultsmentioning

confidence: 99%

“…This makes the proposed approach widely applicable; -a strong experimental performance against popular trackers such as mean shift [16], particle filters [14,17] Despite its use of parts to provide data association, this model should not be confused with approaches to human articulated motion tracking (see [9] for a reference). In articulated motion tracking, the objective is to explicitly track the human's limbs and articulated degrees of freedom whereas in our approach the goal is just that of tracking the human as a global entity.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Tracking people under heavy occlusions by layered data association

Zhang

Perez‐Concha

Piccardi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

One of the main difficulties in video tracking of people arises in scenarios where targets are repeatedly and extensively occluded by other moving objects. These types of occlusions significantly affect the measurements of the person's position, motion, shape and appearance, posing major challenges to correct tracking and data association. In this paper, we present a method for tracking people in videos based on a simplified part-based model only loosely associated with body parts. Data association is provided by a layered data association approach which performs association at feature, part and global levels in a hierarchical fashion. Occlusions are detected and managed at the part level, with corresponding model update strategies. In addition, the tracker does not make any assumption on the target's motion direction, thus allowing tracking to withstand abrupt sideways movements and changes of directions that frequently occur in busy scenes. Experimental results against popular trackers such as mean shift, particle filters and the recent k-shortest paths (KSP) tracker based on a variety of performance indicators and datasets including ETISEO, AVSS 2007 and PETS 2009 show the effectiveness of the proposed tracker.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

Tracking people under heavy occlusions by layered data association

Zhang

Perez‐Concha

Piccardi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…In our system, tracking is based on [14], adding to the particle filter algorithm an adaptive appearance model based on color distributions. The object model is represented by a weighted histogram which takes into account both the color and the shape of the target.…”

Section: Trackingmentioning

confidence: 99%

People detection based on appearance and motion models

García-Martín

Hauptmann

Martinez

2011

2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: AbstractThe main contribution of this paper is a new people detection algorithm based on motion information. The algorithm builds a people motion model based on the Implicit Shape Model (ISM) Framework and the MoSIFT descriptor. We also propose a detection system that integrates appearance, motion and tracking information. Experimental results over sequences extracted from the TRECVID dataset show that our new people motion detector produces results comparable to the state of the art and that the proposed multimodal fusion system improves the obtained results combining the three information sources.

show abstract

“…A majority of these applications lie in the field of feature tracking, in particular, different forms of surveillance from facial recognition [9] to the following of vehicles in traffic [1]. Also of interest is the use of the PF in video compression [15].…”

Section: Particle Filter Algorithmmentioning

confidence: 99%