• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.1-10
• /
• 2014

In this paper, we propose a new view synthesis technique for coding of multi-view color and depth data in arbitrary camera arrangements. We treat each camera position as a 3-D point in world coordinates and build clusters of those vertices. Color and depth data within a cluster are gathered into one camera position using a hierarchical representation based on the concept of layered depth image (LDI). Since one camera can cover only a limited viewing range, we set multiple reference cameras so that multiple LDIs are generated to cover the whole viewing range. Therefore, we can enhance the visual quality of the reconstructed views from multiple LDIs comparing with that from a single LDI. From experimental results, the proposed scheme shows better coding performance under arbitrary camera configurations in terms of PSNR and subjective visual quality.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.982-989
• /
• 2007

In this paper, we propose a 3DTV system that considers user's view point and display environment. The proposed system consists of 3 parts - multi-view encoder/decoder, face-tracker, and 2D/3D converter. The proposed system try to encode multi-view sequence and decode it in accordance with the user's view point and it also gives a stereopsis to the multi-view image by using of 2D/3D conversion which converts decoded two-dimensional(2D) image to three-dimensional(3D) image. Experimental results shows that we are able to correctly reconstruct a stereoscopic view that is exactly corresponding to user's view point.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.773-776
• /
• 1998

In this paper, we propose an efficient multi-view images coding algorithm which finds the optimal texture from the restricted number of multi-view images. The X-Y plane of the normalized object space is divided into triangular patches. The depth value of the node is determined by applying the block based disparity compensation method and then the texture of the each patch is extracted by applying the affine transformation patch is extracted by applying the affine transformation based disparity compensation method to the multi-view images. We restricted the number of images contributed to determining the texture comapred to traditional methods which use all the multi-view images in the texture extraction. Experimental results show that the SNR of images encoded by the proposed algorithm is better than that of imaes encoded by the traditional method by the amount about 0.2dB for the test sets of multi-view images called dragon, kid, city and santa. The recovered images from the encoded data by the proposed method show the better visual images than the recovered images from the encoded data by the traditional methods.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.697-698
• /
• 2006

In this paper, we propose a new scheme to generate multi-view images using a depth-image-based rendering (DIBR) technique. In order to improve the quality of multi-view images at newly exposed areas during mesh-based rendering, we preprocess the depth map using a Gaussian smoothing filter. Previous algorithms apply a smoothing filter to the whole depth map even if the depth map is collapsed. After extracting objects from the depth map, we apply the smoothing filter to their boundaries. Finally, we cannot only maintain the depth quality, but also generate high quality multi-view images. Experimental results show that our proposed algorithm outperforms previous works and supports an efficient depth keying technique.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.1
• /
• pp.27-35
• /
• 2013

This paper proposes a face tracking algorithm for a viewpoint adaptive multi-view synthesis system. The original scene captured by a depth camera contains a texture image and 8 bit gray-scale depth map. From this original image, multi-view images that correspond to the viewer's position can be synthesized using geometrical transformations, such as rotation and translation. The proposed face tracking technique gives a motion parallax cue by different viewpoints and view angles. In the proposed algorithm, the viewer's dominant face, which is established initially from a camera, can be tracked using the statistical characteristics of face colors and deformable templates. As a result, a motion parallax cue can be provided by detecting the viewer's dominant face area and tracking it, even under a heterogeneous background, and synthesized sequences can be displayed successfully.

• Journal of the Optical Society of Korea
• /
• v.19 no.5
• /
• pp.477-486
• /
• 2015

We propose a novel calibration method which can be applied to all kinds of panel-type multi-view displays. We analyze how the angular, the axial, and the lateral misalignment affects the 3D image quality in a panel-type multi-view display. We demonstrate the ray optics simulation with a 3-view slanted parallax barrier system using pentile display for the quantitative calculation. Based on the analysis, we propose a new alignment pattern for all kinds of panel-type multi-view displays. The proposed pattern is sensitive to all of the angular, the axial, and the lateral misalignments. The high spatial frequency images and on and off alignment in the proposed pattern help observers to calibrate the system easily. We theoretically show the generality of the proposed alignment pattern and verify the pattern with image simulations and experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.9
• /
• pp.237-246
• /
• 2016

DIBR (Depth Image Based Rendering) is a multimedia technology that generates the virtual multi-view images using a color image and a depth image, and it is used for creating glasses-less 3-dimensional display contents. This research describes the effect of depth accuracy about the objective quality of DIBR-based multi-view images. It first evaluated the minimum depth quantization bit that enables the minimum distortion so that people cannot recognize the quality degradation. It then presented the comparative analysis of non-uniform domain-division quantization versus regular linear quantization to find out how effectively express the accuracy of the depth information in same quantization levels according to scene properties.

• Journal of Broadcast Engineering
• /
• v.12 no.2
• /
• pp.128-136
• /
• 2007

Since the multi-view video is a set of video sequences captured by multiple array cameras for the same three-dimensional scene, it can provide multiple viewpoint images using geometrical manipulation and intermediate view generation. Although multi-view video allows us to experience more realistic feeling with a wide range of images, the amount of data to be processed increases in proportion to the number of cameras. Therefore, we need to develop efficient coding methods. One of the possible approaches to multi-view video coding is to generate an intermediate image using view interpolation method and to use the interpolated image as an additional reference frame. The previous view interpolation method for multi-view video coding employs fixed size block matching over the pre-determined disparity search range. However, if the disparity search range is not proper, disparity error may occur. In this paper, we propose an efficient view interpolation method using initial disparity estimation, variable block-based estimation, and pixel-level estimation using adjusted search ranges. In addition, we propose a multi-view video coding method based on H.264/AVC to exploit the intermediate image. Intermediate images have been improved about $1{\sim}4dB$ using the proposed method compared to the previous view interpolation method, and the coding efficiency have been improved about 0.5 dB compared to the reference model.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.521-524
• /
• 2004

Recently, acgis of authentication and crcator's copyright has become a matter of great concern by the diffusion of multimedia technique and the growth of the internet and the easily duplicated property of digital data. Consequently, many active researches have been made to protect copyright and to assure integrity by inserting watermark into the digital data. In this paper, watermark is repealed through the entire image and adapted to the content of the image. Achieved by an underlying process of transforming the digital image to the frequency domain by wavelet transform, which has three (vertical, horizontal, diagonal) directions and Multi-resolution features, and then choosing frequency area inferior to the human perceptibility and significant for invisible and robust watermark. We realize wavelet based image watermarking using Machine Vision of LabVIEW.