Combining Color, Depth, and Motion for Video Segmentation

Leens, Jérôme; Pierard, Sébastien; Barnich, Olivier; Droogenbroeck, Marc Van; Wagner, Jean-Marc

doi:10.1007/978-3-642-04667-4_11

Cited by 38 publications

(49 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The overall ranking across categories RC¡ of ¡th method is computed as the mean of the single RM¡ across all the sequences. In the following paragraphs we compare the performance of the following algorithms: the proposed adaptive weighted classifier CL W ; the two weak classifiers CL C and CL D ; the MoG algorithm proposed in [18] M0G RG B-D\ and the binary combinations of the foreground masks obtained by two independent modules based on depth and color data as proposed in [19] (by using MoG) and in [20] (by using ViBe), we refer to these algorithm as M0G Bin and Vibe B ¡". Finally we adapt to the RGBD feature space the neural networks algorithm proposed in [17] (SOM) and the modified MoG algorithm proposed in [14] (MoG Z w).lt has to be noted that no post-processing stages, such as morphological filtering, are applied to the resulting foreground masks.…”

Section: Benchmark Data and Resultsmentioning

confidence: 99%

“…In [20], a multi-camera system combines color data and depth data, obtained with a low resolution ToF camera, for video segmentation. The Vibe algorithm [16] is applied independently to the color and the depth data: the obtained foreground masks are then combined with logical operations and then post processed with morphological operations.…”

Section: Foreground/background Segmentation With Depth Datamentioning

confidence: 99%

See 1 more Smart Citation

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

Camplani

Salgado

2014

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

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.

show abstract

Section: Benchmark Data and Resultsmentioning

confidence: 99%

Section: Foreground/background Segmentation With Depth Datamentioning

confidence: 99%

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

Camplani

Salgado

2014

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

show abstract

“…Such work has either used custom made sensors, as e.g. in [4], or more recently, timeof-flight sensors [8,3,5]. Another large body of similar work is stereo rig segmentation [1,20].…”

Section: Related Workmentioning

confidence: 99%

“…As the scene is static, we cannot exploit either background modelling [8] or tracking [3]. Furthermore, purely colour-based segmentation is particularly brittle here, due to small reflectance variations, shadows, and in particular occlusions [7].…”

Section: Related Workmentioning

confidence: 99%

Channel Coding for Joint Colour and Depth Segmentation

Wallenberg

Felsberg

Forssén

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Segmentation is an important preprocessing step in many applications. Compared to colour segmentation, fusion of colour and depth greatly improves the segmentation result. Such a fusion is easy to do by stacking measurements in different value dimensions, but there are better ways. In this paper we perform fusion using the channel representation, and demonstrate how a state-of-the-art segmentation algorithm can be modified to use channel values as inputs. We evaluate segmentation results on data collected using the Microsoft Kinect peripheral for Xbox 360, using the superparamagnetic clustering algorithm. Our experiments show that depth gradients are more useful than depth values for segmentation, and that channel coding both colour and depth gradients makes tuned parameter settings generalise better to novel images.

show abstract

“…More relevant to this work, [3,4] employ depth information in addition to RGB, to reinforce method accuracy. Moreover, [5] utilizes motion information.…”

Section: Introductionmentioning

confidence: 99%

Foreground Detection with a Moving RGBD Camera

Koutlemanis

Zabulis

Ntelidakis

et al. 2013

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. A method for foreground detection in data acquired by a moving RGBD camera is proposed. The background scene is initially in a reference model. An initial estimation of camera motion is provided by a conventional point cloud registration approach of matched keypoints between the captured scene and the reference model. This initial solution is then refined based on a top-down, model based approach that evaluates candidate camera poses in a Particle Swarm Optimization framework. To evaluate a candidate pose, the method renders color and depth images of the model according to this pose and computes a dissimilarity score of the rendered images to the currently captured ones. This score is based on the direct comparison of color, depth, and surface geometry between the acquired and rendered images, while allowing for outliers due to the potential occurrence of foreground objects, or newly imaged surfaces. Extended quantitative and qualitative experimental results confirm that the proposed method produces significantly more accurate foreground segmentation maps compared to the conventional, baseline feature-based approach.

show abstract

Combining Color, Depth, and Motion for Video Segmentation

Cited by 38 publications

References 15 publications

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

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

Channel Coding for Joint Colour and Depth Segmentation

Foreground Detection with a Moving RGBD Camera

Contact Info

Product

Resources

About