• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.368-378
• /
• 2015

3D conversion technology has been studied over past decades and integrated to commercial 3D displays and 3DTVs. The 3D conversion plays an important role in the augmented functionality of three-dimensional television (3DTV), because it can easily provide 3D contents. Generally, depth cues extracted from a static image is used for generating a depth map followed by DIBR (Depth Image Based Rendering) rendering for producing a stereoscopic image. However except some particular images, the existence of depth cues is rare so that the consistent quality of a depth map cannot be accordingly guaranteed. Therefore, it is imperative to make a 3D conversion method that produces satisfactory and consistent 3D for diverse video contents. From this viewpoint, this paper proposes a novel method with applicability to general types of image. For this, saliency as well as edge is utilized. To generate a depth map, geometric perspective, affinity model and binomic filter are used. In the experiments, the proposed method was performed on 24 video clips with a variety of contents. From a subjective test for 3D perception and visual fatigue, satisfactory and comfortable viewing of 3D contents was validated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1938-1945
• /
• 2001

In this paper, a new scheme for image conversion of the 2D input images into the stereoscopic 3D images by using differential shifting method is proposed. First, the relative depth information is estimated by disparity and occlusion information from the input stereo images and then, each of image objects are segmented by gray-level using the estimated information. Finally, through the differential shifting of the segmented objects according to the horizontal parallax, a stereoscopic 3D image having optimal stereopsis is reconstructed. From some experimental results, it is found that the horizontal disparity can be improved about 1.6dB in PSNR for the reconstructed stereo image using the proposed scheme through comparing to that of the given input image. In the experiment of using the commercial stereo viewer, the reconstructed stereoscopic 3D images, in which each of the segmented objects are horizontally shifted in the range of 4 ∼5 pixels are also found to have the mast improved stereopsis.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.362-371
• /
• 2013

This paper presents a framework of real-time augmented reality on 3-D mobile display with stereo camera tracking. In the framework, camera poses are jointly estimated with the geometric relationship between stereoscopic images, which is based on model-based tracking. With the estimated camera poses, the virtual contents are correctly augmented on stereoscopic images through image rectification. For real-time performance, stereo camera tracking and image rectification are efficiently performed using multiple threads. Image rectification and color conversion are accelerated with a GPU processing. The proposed framework is tested and demonstrated on a commercial smartphone, which is equipped with a stereoscopic camera and a parallax barrier 3-D display.

• Journal of Broadcast Engineering
• /
• v.10 no.2
• /
• pp.139-148
• /
• 2005

This paper presents recent works of the development of MPEG-21 DIA utility software as one of MPEG-21 activities. The main purpose of this work is to make integrated utility software for DIA C/C++ modules in a Java framework. To do this, JNI plays a role of the interface of a main module with C/C++ DIA adaptation modules. Furthermore, DIA and DID parsers are integrated to the utility software. Our software is designed such that all DIA modules are easily integrated. A variety of adaptation modules have been adopted in MPEG-21 standard. Among them, stereoscopic video conversion that is one of DIA adaptation modules is chosen and we show that our utility software is correctly implemented based on experiments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.471-473
• /
• 2011

3D 콘텐츠들은 과거 입체영화 '아바타' 이후로 꾸준히 증가하고 있다. 그리고 인터넷 등을 포함한 사이버 공간의 모든 환경이 제공자 위주에서 사용자 중으로 급격하게 변화하고 있는 상황이다. 이에 사용자들은 원하는 높은 현실감을 바탕으로 디지털 콘텐츠의 입체영상 서비스를 제공받기를 원한다. 그렇기에 3D 콘텐츠의 증가에 따른 Stereoscopic 기술의 필요성이 증대 되었다. 따라서 본 논문은 3차원 입체영상 기술의 기저 기술 중에 하나인 Anaglyph 영상을 연구하기로 하였다. 최종적으로 일반 영상 및 입체 사진을 이용한 스테레오 영상 변환 연구를 진행한다. 세부적으로는 입체 사진(Anaglyph)을 이용한 스테레오 영상 분할, 일반 영상을 이용한 스테레오 영상 편집 연구로 나누어 진행 하였다.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.1-9
• /
• 2014

Previous 2D-3D conversion methods to generate 3D stereo images from 2D sequence consist of labor-intensive procedures in their production pipelines. This paper presents an efficient 2D-3D conversion system based on scene structure reconstruction from image sequence. The proposed system reconstructs a scene space and produces 3D stereo images with texture re-projection. Experimental results show that the proposed method can generate precise 3D contents based on scene structure information. By using the proposed reconstruction tool, the stereographer can collaborate efficiently with workers in production pipeline for 3D contents production.

• Journal of Broadcast Engineering
• /
• v.13 no.4
• /
• pp.427-439
• /
• 2008

This paper proposes a novel method to convert monoscopic soccer videos to stereoscopic videos. Through the soccer video analysis process, we detect shot boundaries and classify soccer frames into long shot or non-long shot. In the long shot case, the depth mapis generated relying on the size of the extracted ground region. For the non-long shot case, the shot is further partitioned into three types by considering the number of ground blocks and skin blocks which is obtained by a simple skin-color detection method. Then three different depth assignment methods are applied to each non-long shot types: 1) Depth estimation by object region extraction, 2) Foreground estimation by using the skin block and depth value computation by Gaussian function, and 3)the depth map generation for shots not containing the skin blocks. This depth assignment is followed by stereoscopic image generation. Subjective evaluation comparing generated depth maps and corresponding stereoscopic images indicate that the proposed algorithm can yield the sense of depth from a single view images.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.9-16
• /
• 2014

Depth-image-based rendering is generally used in real-time 2D-to-3D conversion for 3DTV. However, inaccurate depth maps cause flickering issues between image frames in a video sequence, resulting in eye fatigue while viewing 3DTV. To resolve this flickering issue, we propose a new 2D-to-3D conversion scheme based on fast and robust depth-map generation from a 2D video sequence. The proposed depth-map generation algorithm divides an input video sequence into several cuts using a color histogram. The initial depth of each cut is assigned based on a hypothesized depth-gradient model. The initial depth map of the current frame is refined using color and motion information. Thereafter, the depth map of the next frame is updated using the difference image to reduce depth flickering. The experimental results confirm that the proposed scheme performs real-time 2D-to-3D conversions effectively and reduces human eye fatigue.

• Journal of Broadcast Engineering
• /
• v.19 no.5
• /
• pp.616-626
• /
• 2014

In this paper, we introduce a real-time stereo-to-multiview conversion system using FPGA and GPU. The system is based on two different devices so that it consists of two major blocks. The first block is a disparity estimation block that is implemented on FPGA. In this block, each disparity map of stereoscopic video is estimated by DP(dynamic programming)-based stereo matching. And then the estimated disparity maps are refined by post-processing. The refined disparity map is transferred to the GPU device through USB 3.0 and PCI-express interfaces. Stereoscopic video is also transferred to the GPU device. These data are used to render arbitrary number of virtual views in next block. In the second block, disparity-based view interpolation is performed to generate virtual multi-view video. As a final step, all generated views have to be re-arranged into a single image at full resolution for presenting on the target autostereoscopic 3D display. All these steps of the second block are performed in parallel on the GPU device.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.205-208
• /
• 2015

3D 입체영상을 제작하기 위해서는 2D 영상제작에 비해 오랜 제작 기간과 많은 비용이 발생한다. 비용 절감을 위해 기존의 2D 영상을 3D 입체영상으로 변환하는 연구가 진행되고 있다. 2D 영상을 3D 입체영상으로 변환하는 방식은 자동변환방법과 수동변환방법으로 구분할 수 있으며, 고품질의 2D-3D 변환 영상을 획득하기 위해서는 깊이정보 지도(Depth map chart)를 활용한 수동변환 방법을 많이 사용되고 있다. 하지만 2D-3D 수동변환에 사용되는 깊이정보 지도의 정량적 분석 데이터가 부족하여 사용자가 변환한 이미지에 대한 정확한 기준 깊이값 설정이 어려운 단점이 있다. 본 논문에서는 깊이정보 지도의 깊이값 정보에 대한 정량적 분석 데이터를 바탕으로 한 2D-3D 수동변환 변화범위를 제시함으로써 적정한 영상 변화를 유도할 수 있도록 한다.