Efficient multiview depth representation based on image segmentation

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

2012

Self Cite

This paper presents a novel depth image compression algorithm for both 3D Television (3DTV) and Free Viewpoint Television (FVTV) services. The proposed scheme adopts the K-means clustering algorithm to segment the depth image into K segments. The resulting segmented image is losslessly compressed and transmitted to the decoder. The depth image is then compressed using a bi-modal block encoder, where the smooth blocks are predicted using direct spatial prediction. On the other hand, blocks containing depth discontinuities are approximated using a novel depth discontinuity predictor. The residual information is then compressed using a lossy compression strategy and transmitted to the receiver. Simulation results indicate that the proposed scheme outperforms the state of the art spatial video coding systems available today such as JPEG and H.264/AVC Intra. Moreover, the proposed scheme manages to outperform specialized depth image compression algorithms such as the one proposed by Zanuttigh and Cortelazzo.

Section: Introductionmentioning

confidence: 93%

“…The correlation between video and depth information was exploited through color segmentation in [17,18]. However, the performance of the method presented in [17] significantly drops at high rates while the method published in [18] manages to outperform H.264/AVC Intra at all rates.…”

Section: Introductionmentioning

confidence: 99%

Efficient Depth Image Compression Using Accurate Depth Discontinuity Detection and Prediction

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

2012

Self Cite

“…Providing the exact contours for boundary reconstruction of each segment is on the other hand prohibitively expensive due to the sheer amount of data required, which would in turn reduce the viability of employing the segmentation algorithm [27]. Our earlier work [38], overcomes such a problem by exploiting the degree of correspondence present between the depth image and the color intensity image which are both characterizing a unique scene from an identical viewpoint and timestamp. This technique considers the color intensity image to be provided to the decoder by means of traditional coding algorithms.…”

Section: Depth Map Representation Techniquementioning

confidence: 99%

“…The required properties for segmentation can be fulfilled by employing a Normalised Graph-Cut approach [34], [35]. Further detail and elucidation on the manner in which the segmentation algorithm was employed is documented in [38].…”

Section: Depth Map Representation Techniquementioning

confidence: 99%

Performance improvement of segmentation-based depth representation in 3D imagery by region merging

Raffaele

Camilleri

The 2012 International Conference on Advanced Technologies for Communications

et al. 2012

The feasible implementation of immersive 3D video systems entails the need for a substantial reduction in the amount of image information necessary for representation. Multiview image rendering algorithms based on depth data have radically reduced the number of images required to reconstruct a 3D scene. Nonetheless, the compression of depth maps still poses several challenges due to the particular nature and characteristics of the data. To this end, this paper outlines a depth representation technique, developed in our earlier work, that exploits the correlation intrinsically present between color intensity and depth images capturing a natural scene. In this technique, a segmentation-based algorithm that is backwards compatible with conventional video coding systems is implemented. The effectiveness of our previous technique is enhanced in this contribution by a region merging process on the segmented regions, which results in a decrease in the amount of information necessary for transmission or storage of multiview image data by a factor of 20.5 with respect to the reference H.264/AVC coding methodology. This is furthermore achieved whilst maintaining a 3D image reconstruction and viewing quality which is quasi identical to the referenced approach.peer-reviewe

“…These depth map compression algorithms manage to preserve the edge discontinuities to achieve high quality virtual views. The correlation between color and depth images was exploited in [13], [14]. However, the performance of the former approach significantly drops at high rates while that of the latter suffers from the fact that the discontinuities present in depth and color images are generally not perfectly aligned.…”

mentioning

confidence: 99%

Exploiting color-depth image correlation to improve depth map compression

Gambin

2013

Eurocon 2013

Abstract-The multimedia signal processing community has recently identified the need to design depth map compression algorithms which preserve depth discontinuities in order to improve the rendering quality of virtual views for Free Viewpoint Video (FVV) services. This paper adopts contour detection with surround suppression on the color video to approximate the foreground edges present in the depth image. Displacement estimation and compensation is then used to improve this prediction and reduce the amount of side information required by the decoder. Simulation results indicate that the proposed method manages to accurately predict around 64% of the blocks. Moreover, the proposed scheme achieves a Peak Signal-to-Noise Ratio (PSNR) gain of around 4.9 -6.6 dB relative to the JPEG standard and manages to outperform other state of the art depth map compression algorithms found in literature.Index Terms-3D television, depth map compression, displacement estimation and compensation, edge detection, surround suppression I. INTRODUCTION Advances in technology have contributed to the development of new applications such as 3D Television (3DTV) and Free Viewpoint Video (FVV), which have recently started to attract interest within the marketplace. The multi-view video plus depth (MVD) [1] format enables the generation of an infinite set of videos using a finite set of color and corresponding depth videos [2]. The MVD format significantly reduces the amount of information needed to deploy these services. Moreover, in order to make these applications more viable, both color and depth videos need to be compressed. However, the quality of the rendered views is significantly dependent on the quality of the depth video.Traditional image and video compression standards produce blurring artifacts along depth discontinuities, which negatively affect the Quality of Experience (QoE) of the rendered virtual views [3], [4]. The authors in [5] have demonstrated that higher rendering quality can be perceived when employing depth map compression strategies which preserve edge boundaries. Following this observation the same authors have proposed to reshape the dynamic range and use Region of Interest (RoI) coding to improve the performance of traditional image compression standards. Directional transforms were considered in [3], [6] which are highly computational intensive.