• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2010년도 하계학술대회
• /
• pp.241-243
• /
• 2010

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

• 한국정보통신학회논문지
• /
• 제16권7호
• /
• pp.1477-1486
• /
• 2012

본 논문에서는 가상시점 깊이영상 생성 기법을 이용한 다양한 시점의 CGH(computer generated hologram) 생성 시스템을 제안한다. 제안한 시스템에서는 먼저 TOF(time of flight) 깊이 카메라를 이용하여 신뢰도 높은 기준시점 깊이영상을 획득하고 카메라 보정 과정을 통해 기준시점 카메라들의 카메라 파라미터를 추출한다. 가상시점 카메라의 위치가 정의되면 기준시점 카메라와의 거리와 위치를 고려하여 최적의 기준시점 카메라들을 선택한다. 가상시점 카메라와 가장 가까운 기준시점 카메라를 주 기준시점으로 결정하고 가상시점 깊이영상을 생성한다. 주 기준시점 카메라와 위치가 반대인 기준시점 카메라를 보조 기준시점으로 선택하여 가상시점 깊이영상을 생성한다. 주 기준시점을 통해 생성된 가상시점 깊이영상에 나타나는 가려짐 영역을 보조 기준시점으로 생성된 가상시점 깊이영상으로부터 찾아 보상한다. 보상이 되지 않고 남은 홀영역은 주변값 중 가장 작은 값으로 채워 최종 가상시점 깊이영상을 생성한다. 최종 가상시점 깊이 영상을 이용하여 CGH를 생성한다. 실험을 통해 기존의 기법보다 제안하는 가상시점 깊이영상 합성 시스템의 성능이 우수함을 확인하였다.

• Journal of information and communication convergence engineering
• /
• 제11권2호
• /
• pp.132-138
• /
• 2013

In this paper, an accelerated generation algorithm to effectively generate an elemental image array in computational integral imaging system is proposed. In the proposed method, the depth information of 3D object is extracted from the images picked up by a stereo camera or depth camera. Then, the elemental image array can be generated by using the proposed accelerated generation algorithm with the depth information of 3D object. The resultant 3D image generated by the proposed accelerated generation algorithm was compared with that the conventional direct algorithm for verifying the efficiency of the proposed method. From the experimental results, the accuracy of elemental image generated by the proposed method could be confirmed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권3호
• /
• pp.1058-1070
• /
• 2014

There are two major ways to implement depth estimation, multiple image depth estimation and single image depth estimation, respectively. The former has a high hardware cost because it uses multiple cameras but it has a simple software algorithm. Conversely, the latter has a low hardware cost but the software algorithm is complex. One of the recent trends in this field is to make a system compact, or even portable, and to simplify the optical elements to be attached to the conventional camera. In this paper, we present an implementation of depth estimation with a single image using a graphics processing unit (GPU) in a desktop PC, and achieve real-time application via our evolutional algorithm and parallel processing technique, employing a compute shader. The methods greatly accelerate the compute-intensive implementation of depth estimation with a single view image from 0.003 frames per second (fps) (implemented in MATLAB) to 53 fps, which is almost twice the real-time standard of 30 fps. In the previous literature, to the best of our knowledge, no paper discusses the optimization of depth estimation using a single image, and the frame rate of our final result is better than that of previous studies using multiple images, whose frame rate is about 20fps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권9호
• /
• pp.1613-1631
• /
• 2011

Several metrics have been reported in the literature to assess stereo image quality, mostly based on visual attention or human visual sensitivity based distortion prediction with the help of disparity information, which do not consider the combined aspects of human visual processing. In this paper, visual attention and depth assisted stereo image quality assessment model (VAD-SIQAM) is devised that consists of three main components, i.e., stereo attention predictor (SAP), depth variation (DV), and stereo distortion predictor (SDP). Visual attention is modeled based on entropy and inverse contrast to detect regions or objects of interest/attention. Depth variation is fused into the attention probability to account for the amount of changed depth in distorted stereo images. Finally, the stereo distortion predictor is designed by integrating distortion probability, which is based on low-level human visual system (HVS), responses into actual attention probabilities. The results show that regions of attention are detected among the visually significant distortions in the stereo image pair. Drawbacks of human visual sensitivity based picture quality metrics are alleviated by integrating visual attention and depth information. We also show that positive correlation with ground-truth attention and depth maps are increased by up to 0.949 and 0.936 in terms of the Pearson and the Spearman correlation coefficients, respectively.

• International Journal of Contents
• /
• 제14권3호
• /
• pp.1-6
• /
• 2018

For 3D display applications, auto-stereoscopic display methods that can provide 3D images without glasses have been actively developed. This paper is concerned with developing a display system for elemental images of real space using integral imaging. Unlike the conventional method, which reduces a color image to the level as much as a generated depth image does, we have minimized original color image data loss by generating an enlarged depth image with interpolation methods. Our method was efficiently implemented by applying a GPU parallel processing technique with OpenCL to rapidly generate a large amount of elemental image data. We also obtained experimental results for displaying higher quality integral imaging rather than one generated by previous methods.

• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.67-71
• /
• 2016

This paper addresses a problem of defocus map recovery from single image. We describe a simple effective approach to estimate the spatial value of defocus blur at the edge location of the image. At first, we perform a re-blurring process using Gaussian function with input image, and calculate a gradient magnitude ratio with blurring amount between input image and re-blurred image. Then we get a full defocus map by propagating the blur amount at the edge location. Experimental result reveals that our method outperforms a reliable estimation of depth map, and shows that our algorithm is robust to noise, inaccurate edge location and interferences of neighboring edges within input image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3217-3238
• /
• 2018

In this paper, a depth image up-sampling method is put forward by using pixel classifying and jointed bilateral filtering. By analyzing the edge maps originated from the high-resolution color image and low-resolution depth map respectively, pixels in up-sampled depth maps can be classified into four categories: edge points, edge-neighbor points, texture points and smooth points. First, joint bilateral up-sampling (JBU) method is used to generate an initial up-sampling depth image. Then, for each pixel category, different refinement methods are employed to modify the initial up-sampling depth image. Experimental results show that the proposed algorithm can reduce the blurring artifact with lower bad pixel rate (BPR).

• 한국통신학회논문지
• /
• 제30권4C호
• /
• pp.239-246
• /
• 2005

본 논문에서는 영상의 RGB 정보와 화소단위의 8비트 깊이 정보를 이용하여 현재의 영상과 스테레오 쌍이 되는 가상의 우 영상을 생성한다. 이 과정에서 깊이 정보를 시차 정보로 변환하고, 생성된 시차정보를 이용하여 우 영상을 생성하게 된다. 또한 스테레오 영상을 합성한 후 회전(rotation)과 이동(translation) 등의 기하학적 변환을 이용하여 관찰자의 위치를 고려한 다시점 스테레오 영상을 합성하는 기법을 제안하고, 깊이 정보와 시차 정보와의 관계를 분석하여 화소 단위의 실시간 처리를 위한 LUT(look-up table) 방식의 고속 기법도 제안한다. 실험 결과 SD급 영상의 경우 8비트 깊이 정보만을 가지고 11시점의 스테레오 영상을 실시간으로 합성할 수 있다.

• 한국통신학회논문지
• /
• 제34권2C호
• /
• pp.186-193
• /
• 2009

다시점 비디오는 데이터 양이 매우 많아서 이를 효과적으로 저장하고 전송하기 위해서는 새로운 압축 부호화의 기술 개발이 필수적이다. 계층적 깊이 영상은 다시점 비디오를 효과적으로 부호화할 수 있는 방법으로 여러 시점의 컬러와 깊이 영상을 합성하여 하나의 데이터 구조로 만든 것이다. 본 논문에서는 실제 거리비교, 오버랩 문제해결, YCrCb 컬러변환을 이용한 효율적인 계층적 깊이 영상 표현을 통해서 다시점 영상에 대한 압축 효율을 향상시키는 방법을 제안하였다. 실험 결과를 통해서 압축성능 향상과 우수한 복원 성능을 얻을 수 있었다.