Adaptive Foreground/Background Segmentation Using Multiview Silhouette Fusion

Feldmann, Tobias; Dießelberg, Lars; Wörner, Annika

doi:10.1007/978-3-642-03798-6_53

Cited by 10 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The segmentation via probabilistic 3d fusion proposed in [5] is based on two ideas: First, a probabilistic 2d segmentation of fore-and background in all camera images of a static, calibrated multi camera setup is performed based on color distribution models. To make this segmentation more robust and adaptive, the second part integrates 3d scene information reconstructed from all cameras.…”

Section: Segmentation By Probabilistic 3d Fusionmentioning

confidence: 99%

“…The background model in eq. 2 is updated continuously by integration of all previous frames over time by utilizing an online Expectation Maximization (EM) approach as presented in [5].…”

Section: Fore-and Background Modelmentioning

confidence: 99%

“…Regarding the modality, image based human motion capture has been done monocular [1], with stereo [2], multi view [3,4,5] or multi view stereo setups [6].…”

Section: Introductionmentioning

confidence: 99%

“…The estimation of foreground from the image data can be realized by image differencing over time [7], by using color model coherence by integrating appropriate a priori knowledge of fore-and background [8,9] or by integrating 3d knowledge from stereo [2] or n-view reconstructions [4,5]. If colors are used for foreground segmentation, the approaches can be separated in simple per channel differencing approaches, codebooks models [10] and mixture models [11].…”

Section: Introductionmentioning

confidence: 99%

“…Based on the color models, the segmentation is usually performed based on probabilities [5] or energy minimization, e.g. level set approaches [12,13] or graph cuts [14].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

N-View Human Silhouette Segmentation in Cluttered, Partially Changing Environments ,

Feldmann

Scheuermann

Rosenhahn

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The segmentation of foreground silhouettes of humans in camera images is a fundamental step in many computer vision and pattern recognition tasks. We present an approach which, based on color distributions, estimates the foreground by automatically integrating data driven 3d scene knowledge from multiple static views. These estimates are integrated into a level set approach to provide the final segmentation results. The advantage of the presented approach is that ambiguities based on color distributions of the fore-and background can be resolved in many cases utilizing the integration of implicitly extracted 3d scene knowledge and 2d boundary constraints. The presented approach is thereby able to automatically handle cluttered scenes as well as scenes with partially changing backgrounds and changing light conditions.

show abstract

Section: Segmentation By Probabilistic 3d Fusionmentioning

confidence: 99%

“…The background model in eq. 2 is updated continuously by integration of all previous frames over time by utilizing an online Expectation Maximization (EM) approach as presented in [5].…”

Section: Fore-and Background Modelmentioning

confidence: 99%

“…Regarding the modality, image based human motion capture has been done monocular [1], with stereo [2], multi view [3,4,5] or multi view stereo setups [6].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Based on the color models, the segmentation is usually performed based on probabilities [5] or energy minimization, e.g. level set approaches [12,13] or graph cuts [14].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

N-View Human Silhouette Segmentation in Cluttered, Partially Changing Environments ,

Feldmann

Scheuermann

Rosenhahn

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Spatio-Temporal Optimization for Foreground/Background Segmentation

Feldmann

2011

Computer Vision – ACCV 2010 Workshops

View full text Add to dashboard Cite

N-tuple Color Segmentation for Multi-view Silhouette Extraction

Djelouah

Franco

Boyer

et al. 2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

We present a new method to extract multiple segmentations of an object viewed by multiple cameras, given only the camera calibration. We introduce the n-tuple color model to express interview consistency when inferring in each view the foreground and background color models permitting the final segmentation. A color n-tuple is a set of pixel colors associated to the n projections of a 3D point. The first goal is set as finding the MAP estimate of background/foreground color models based on an arbitrary sample set of such n-tuples, such that samples are consistently classified, in a soft way, as "empty" if they project in the background of at least one view, or "occupied" if they project to foreground pixels in all views. An Expectation Maximization framework is then used to alternate between color models and soft classifications. In a final step, all views are segmented based on their attached color models. The approach is significantly simpler and faster than previous multi-view segmentation methods, while providing results of equivalent or better quality.

show abstract

Adaptive Foreground/Background Segmentation Using Multiview Silhouette Fusion

Cited by 10 publications

References 13 publications

N-View Human Silhouette Segmentation in Cluttered, Partially Changing Environments ,

N-View Human Silhouette Segmentation in Cluttered, Partially Changing Environments ,

Spatio-Temporal Optimization for Foreground/Background Segmentation

N-tuple Color Segmentation for Multi-view Silhouette Extraction

Contact Info

Product

Resources

About