Depth gradient based segmentation of overlapping foreground objects in range images

Journal of Visual Communication and Image Representation

2014

Low cost RGB-D cameras such as the Microsoft's Kinect or the Asus's Xtion Pro are completely changing the computer vision world, as they are being successfully used in several applications and research areas. Depth data are particularly attractive and suitable for applications based on moving objects detection through foreground/background segmentation approaches; the RGB-D applications proposed in literature employ, in general, state of the art foreground/background segmentation techniques based on the depth information without taking into account the color information. The novel approach that we propose is based on a combination of classifiers that allows improving background subtraction accuracy with respect to state of the art algorithms by jointly considering color and depth data. In particular, the combination of classifiers is based on a weighted average that allows to adaptively modifying the support of each classifier in the ensemble by considering foreground detections in the previous frames and the depth and color edges. In this way, it is possible to reduce false detections due to critical issues that can not be tackled by the individual classifiers such as: shadows and illumination changes, color and depth camouflage, moved background objects and noisy depth measurements. Moreover, we propose, for the best of the author's knowledge, the first publicly available RGB-D benchmark dataset with hand-labeled ground truth of several challenging scenarios to test background/foreground segmentation algorithms.

Section: Benchmark Data and Resultsmentioning

confidence: 99%

“…MoG is also proposed in [19], where depth and infrared data are combined to detect foreground objects. Two independent background models are built and each pixel is classified as background or foreground only if the two models matching conditions agree.…”

Section: Foreground/background Segmentation With Depth Datamentioning

confidence: 99%

Background foreground segmentation with RGB-D Kinect data: An efficient combination of classifiers

Journal of Visual Communication and Image Representation

2014

“…The overall ranking RC; for the /th method is then computed taking into account all the sequences RC¡ = -£RM¡, [31], which computes abinary combination of foreground masks obtained by two independent modules using MoG; VibeBin [23], which is based on a binary combination of foreground masks obtained by means of the ViBe algorithm [4]; PBAS [18], which first models the background using the recent history of pixel values, and then computes the foreground using a decision threshold calculated dynamically for each pixel; SOBS [25], which adopts a neural-network based approach to detect foreground objects without making any assumption about the pixel distribution; and CLw [9], which uses a probabilistic classifier to fuse a set of foreground masks, which are computed by a mixture of Gaussian approach that uses color and depth information. Regarding the PBAS and SOBS algorithms, we have to state that they have been extended to use RGB-D imagery, since originally they only employed color imagery.…”

Section: Ac\b S(a B) = (20) Aubmentioning

confidence: 99%

“…The MoG algorithm has been also used in [31], where depth and infrared data are combined for moving object detection. In this work, two independent background models are estimated, and the corresponding foreground regions are identified when the classification of these two models agree.…”

Section: Introductionmentioning

confidence: 99%

Advanced background modeling with RGB-D sensors through classifiers combination and inter-frame foreground prediction

Blanco

Machine Vision and Applications

et al. 2013

An innovative background modeling technique that is able to accurately segment foreground regions in RGB-D imagery (RGB plus depth) has been presented in this paper. The technique is based on a Bayesian framework that efficiently fuses different sources of information to segment the foreground. In particular, the final segmentation is obtained by considering a prediction of the foreground regions, carried out by a novel Bayesian Network with a depth-based dynamic model, and, by considering two independent depth and color-based mixture of Gaussians background models. The efficient Bayesian combination of all these data reduces the noise and uncertainties introduced by the color and depth features and the corresponding models. As a result, more compact segmentations, and refined foreground object silhouettes are obtained. Experimental results with different databases suggest that the proposed technique outperforms existing state-of-the-art algorithms.

“…The MoG algorithm has been also used by Stormer et al (2010) to combine depth and infrared data. Two independent per-pixel background models are built, and pixels are classified as foreground when both models agree, otherwise the pixels are classified as background.…”

Section: Introductionmentioning

confidence: 99%

Multi-sensor background subtraction by fusing multiple region-based probabilistic classifiers

del-Blanco

Pattern Recognition Letters

et al. 2014

In the recent years, the computer vision community has shown great interest on depth-based applications thanks to the performance and flexibility of the new generation of RGB-D imagery. In this paper, we present an efficient background subtraction algorithm based on the fusion of multiple region-based classifiers that processes depth and color data provided by RGB-D cameras. Foreground objects are detected by combining a region-based foreground prediction (based on depth data) with different background models (based on a Mixture of Gaussian algorithm) providing color and depth descriptions of the scene at pixel and region level. The information given by these modules is fused in a mixture of experts fashion to improve the foreground detection accuracy. The main contributions of the paper are the region-based models of both background and foreground, built from the depth and color data. The obtained results using different database sequences demonstrate that the proposed approach leads to a higher detection accuracy with respect to existing state-of-the-art techniques.