Real-time multi-colourspace hand segmentation

Spruyt, Vincent; Ledda, Alessandro; Geerts, Stig

doi:10.1109/icip.2010.5653220

Cited by 21 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because common prediction methods in probabilistic trackers (random walk, constant velocity, constant acceleration) often fail to predict real-life (non-linear) motion, yet are still frequently used (for example [8] and [9]) we propose a more accurate method by introducing an advanced deterministic tracker within these probabilistic trackers. As we intend to include spatial information, CCA was chosen for its computational simplicity.…”

Section: Our Approachmentioning

confidence: 99%

A Canonical Correlation Analysis based motion model for probabilistic visual tracking

Heyman

Spruyt

Grünwedel

et al. 2012

2012 Visual Communications and Image Processing

Self Cite

View full text Add to dashboard Cite

Particle filters are often used for tracking objects within a scene. As the prediction model of a particle filter is often implemented using basic movement predictions such as random walk, constant velocity or acceleration, these models will usually be incorrect. Therefore, this paper proposes a new approach, based on a Canonical Correlation Analysis (CCA) tracking method which provides an object specific motion model. This model is used to construct a proposal distribution of the prediction model which predicts new states, increasing the robustness of the particle filter. Results confirm an increase in accuracy compared to state-of-the-art methods.

show abstract

Section: Our Approachmentioning

confidence: 99%

A Canonical Correlation Analysis based motion model for probabilistic visual tracking

Heyman

Spruyt

Grünwedel

et al. 2012

2012 Visual Communications and Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Offline color statistics are calculated in RGB color space, whereas online statistics are calculated in the HSV color space. This allows us to incorporate multiple color spaces into our algorithm, yielding better illumination independence [8].…”

Section: Particle Filter Integrationmentioning

confidence: 99%

“…A Bayesian skin classifier is trained offline and used to generate a likelihood map, as described in [8]. This skin likelihood is combined with motion detection and probabilistic background subtraction.…”

Section: Particle Filter Integrationmentioning

confidence: 99%

Real-time, long-term hand tracking with unsupervised initialization

Spruyt¹,

Ledda²,

Philips

2013

2013 IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

This paper proposes a complete tracking system that is capable of long-term, real-time hand tracking with unsupervised initialization and error recovery. Initialization is steered by a three-stage hand detector, combining spatial and temporal information. Hand hypotheses are generated by a random forest detector in the first stage, whereas a simple linear classifier eliminates false positive detections. Resulting detections are tracked by particle filters that gather temporal statistics in order to make a final decision. The detector is scale and rotation invariant, and can detect hands in any pose in unconstrained environments. The resulting discriminative confidence map is combined with a generative particle filter based observation model to enable robust, long-term hand tracking in real-time. The proposed solution is evaluated using several challenging, publicly available datasets, and is shown to clearly outperform other state of the art object tracking methods.

show abstract

“…Examples of particle filters include sequential importance sampling PFs, auxiliary sampling importance re-sampling PFs, sampling importance re-sampling PFs etc. The interested reader is referred to [8,93,109] for an extended reading.…”

Section: Particle Filtersmentioning

confidence: 99%

“…SIR particle filters were used by Spruyt et al for hand tracking [109]. A combination of motion and skin cues were used as measures used in the particle filters.…”

Section: Particle Filtersmentioning

confidence: 99%