Occlusion Management in Sequential Mean Field Monte Carlo Methods

Medrano, Carlos; Igual, Raúl; Orrite, Carlos; Plaza, Inmaculada

doi:10.1007/978-3-642-21257-4_55

Cited by 1 publication

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been selected because of our previous experience with it and because it gives acceptable tracking results, which we are trying to reproduce with less computation time. The details can be found in [14, 15]. We just present the basic ideas for completeness.…”

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

“…The likelihood has to take into account occlusions. Examples of such a likelihood can be found in [15, 16], where the background and the foreground information as well as the visible regions for each target are taken into account. ψ ( x i , t , x j , t ) is a pairwise interaction term that prevents targets from occupying the same place, by decreasing the probability when this happens [14, 17]. The main steps of SMFMC are the following two: first, a particle filter is executed for each target using the dynamical model to propagate particles to get new states

x_{i, t}^{n}

(object i and particle n ).…”

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

“…Roughly speaking, each particle of a given object sees the other targets as if they were in their average states. In [15], this is shown to be a first‐order approximation to a set of mean field equations.…”

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

“…The likelihood has to take into account occlusions. Examples of such a likelihood can be found in [15,16], where the background and the foreground information as well as the visible regions for each target are taken into account. † ψ(x i,t , x j,t ) is a pairwise interaction term that prevents targets from occupying the same place, by decreasing the probability when this happens [14,17].…”

Section: Mean Field Trackingmentioning

confidence: 99%

See 4 more Smart Citations

Adaptive tracking algorithms to improve the use of computing resources

Igual¹,

Medrano²,

Plaza³

et al. 2013

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

Computation time is a fundamental concern when tracking objects in real time, especially in complex scenes. Inspired by previous works on automatic failure detection and in situ evaluation of tracking, the authors propose in this study an adaptive tracking algorithm based on pattern recognition techniques, which uses more computing resources only when tracking is likely to fail. Tracking quality is discretised into two binary values and a supervised classifier is trained using some features obtained from the tracking itself and ground truth data. During the operation of the classifier, whenever the tracking quality diminishes, the tracking algorithm reacts in a predefined way in order to avoid the failure. Two specific examples are presented, in which the action taken is different when a potential risk situation is detected: either the number of particles increases or the algorithm used to track changes. The experimental work shows that these methods can be easily implemented with a substantial reduction of processing time but with little tracking performance loss.

show abstract

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

x_{i, t}^{n}

(object i and particle n ).…”

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

Section: Adapting the Number Of Particlesmentioning

confidence: 99%

“…The likelihood has to take into account occlusions. Examples of such a likelihood can be found in [15,16], where the background and the foreground information as well as the visible regions for each target are taken into account. † ψ(x i,t , x j,t ) is a pairwise interaction term that prevents targets from occupying the same place, by decreasing the probability when this happens [14,17].…”

Section: Mean Field Trackingmentioning

confidence: 99%

See 3 more Smart Citations