• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.492-496
• /
• 2020

The visibility deteriorates in hazy weather and it is difficult to accurately recognize information captured by the camera. Research is being actively conducted to remove haze so that camera-based applications such as object localization/detection and lane recognition can operate normally even in hazy weather. In this paper, we propose a nonlinear model for depth map estimation through an extensive analysis that the difference between brightness and saturation in hazy image increases non-linearly with the depth of the image. The quantitative evaluation(MSE, SSIM, TMQI) shows that the proposed haze removal method based on the nonlinear model is superior to other state-of-the-art methods.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.517-526
• /
• 2008

Stereo vision is a fundamental method for measuring 3D structures by observing them from two cameras placed on different positions. In order to reconstruct 3D structures, it is necessary to create a disparity map from a pair of stereo images. To create a disparity map we compute the matching cost for each point correspondence and compute the disparity that minimizes the sum of the whole matching costs. In this paper, we propose a method to estimate a dense disparity map using region segmentation. We segment each scanline using region homogeneity properties. Using the segmented regions, we prohibit false matches in the stereo matching process. Disparities for pixels that failed in matching are filled by interpolating neighborhood disparities. We applied the proposed method to various stereo images of real environments. Experimental results showed that the proposed method is stable and potentially viable in practical applications.

• Journal of Broadcast Engineering
• /
• v.16 no.4
• /
• pp.596-601
• /
• 2011

In this paper, we propose a fast depth-image-based rendering method to generate a virtual view image in real-time using a graphic processor unit (GPU) for a 3D broadcasting system. Before the transmission, we encode the input 2D+depth video using the H.264 coding standard. At the receiver, we decode the received bitstream and generate a stereo video using a GPU which can compute in parallel. In this paper, we apply a simple and efficient hole filling method to reduce the decoder complexity and reduce hole filling errors. Besides, we design a vertical parallel structure for a forward mapping process to take advantage of the single instruction multiple thread structure of GPU. We also utilize high speed GPU memories to boost the computation speed. As a result, we can generate virtual view images 15 times faster than the case of CPU-based processing.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.1_2
• /
• pp.59-66
• /
• 2004

In this paper, a fast 3D model extraction algorithm with an enhanced PBIL of preserving depth consistency is proposed for the extraction of 3D depth information from 2D images. Evolutionary computation algorithms are efficient search methods based on natural selection and population genetics. 2D disparity maps acquired by conventional matching algorithms do not match well with the original image profile in disparity edge regions because of the loss of fine and precise information in the regions. Therefore, in order to decrease the imprecision of disparity values and increase the quality of matching, a compact genetic algorithm is adapted for matching environments, and the adaptive window, which is controlled by the complexity of neighbor disparities in an abrupt disparity point is used. As the result, the proposed algorithm showed more correct and precise disparities were obtained than those by conventional matching methods with relaxation scheme.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.35-38
• /
• 2011

최근 3DTV 의 급격한 활성화로 스테레오 영상 콘텐츠 제작이 크게 증가하고 있다. 스테레오 영상은 일반 2D 영상과 달리 깊이(depth)가 존재하므로 자막과 같은 그래픽의 삽입에서 그 깊이를 반드시 고려해야 한다. 또한 시각피로를 줄이기 위해 스테레오 촬영 시 영상의 변이맵(disparity map)을 실시간 관찰할 필요성도 요구되고 있다. 본 논문에서는 최신의 그래픽 하드웨어를 이용하여 듀얼스트림 HD 영상을 실시간으로 스테레오 정합하는 방법을 제안한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.696-699
• /
• 2004

본 논문은 현실감 있는 영상 기반 환경 모델의 생성을 위해 영상 분할 기반 환경 모델링 방법을 제안한다. 입력 영상을 환경 특성에 따라 바닥면, 천정(하늘), 주변 물체들로 분할하고 분할된 바닥면이나 천정을 참조 평면으로 설정하고 주변 물체들의 깊이값을 계산함으로써 상세한 환경 모델을 얻을 수 있다. 영상 분할 환경 모델링 방법은 환경 맵에 적용하기 용이하며 환경의 특성에 따른 깊이값 추출 방법으로 손쉽게 환경 모델링이 가능하다. 또한, 시점이 이동되고 시차를 갖는 환경의 표현이 가능하다.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.411-412
• /
• 2019

증강현실기술에서 가상의 객체를 주변 환경과 이질감 없이 가시화 하는 것이 중요하다. 본 논문에서는 스테레오 카메라로부터 얻어진 깊이 맵을 활용하여 객체와 그림자를 분석하고 주변의 조명 환경을 해석하여 조명 정보를 추정하는 방법을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2006.11a
• /
• pp.59-62
• /
• 2006

본 논문에서는 OpenGL Rendering을 이용한 모델기반 3D 다시점 영상의 객체 구현을 위한 구성과 각 모듈에 적용되는 알고리즘에 대해 중점적으로 연구하였다. 한 장의 텍스쳐 이미지와 깊이 맵(Depth Map)을 가지고 다시점 객체를 생성하기 위해, 먼저 깊이 정보의 전처리 과정을 거친다. 전처리 된 깊이 정보는 OpenGL상에서의 일정 간격의 꼭지점(Vertex) 정보로 샘플링 된다. 샘플링 된 꼭지점 정보는 깊이 정보를 z값으로 가지는 3차원 공간 좌표상의 점이다. 이 꼭지점 정보를 기반으로 텍스쳐 맵핑 (texture mapping)을 위한 폴리곤(polygon)을 구성하기 위해 딜루이니 삼각화(Delaunay Triangulations) 알고리즘이 적용되었다. 이렇게 구성된 폴리곤 위에 텍스쳐 이미지를 맵핑하여 OpenGL의 좌표 연산을 통해 시점을 자유롭게 조정할 수 있는 객체를 만들었다. 제한된 하나의 이미지와 깊이 정보만을 가지고 좀 더 넓은 범위의 시점을 가지는 다시점 객체를 생성하기 위해, 새로운 꼭지점을 생성하여 폴리곤을 확장시켜 기존보다 더 넓은 시점을 확보할 수 있었다. 또한 렌더링된 모델의 경계 영역 부분의 깊이정보 평활화를 통해 시각적인 개선을 이룰 수 있었다.

• Journal of Broadcast Engineering
• /
• v.2 no.2
• /
• pp.216-224
• /
• 1997

In this paper, we propose a depth information extraction method for intermediate image synthesis. As stereo matching method, MBS(Multiple-Baseline Stereo) method has been proposed, in which the matching accuracy increases by using the multiple camera, but there are some inherent problems such as computational complexity, boundary overreach(BO) in depth map, and occlusion. So, we propose the modified version of MBS so called Multi-Resolution MBS(MR-MBS). Moreover, we also propose an adaptive occlusion area processing technique to improve the accuracy of the depth information in occlusion area.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.119-126
• /
• 2012

Recently, we used to recognize for human motions with some recognition algorithms. examples, HMM, DTW, PCA etc. In many human motions, we concentrated our research on recognizing fighting motions. In previous work, to obtain the fighting motion data, we used motion capture system which is developed with some active markers and infrared rays cameras and 3 dimension information converting algorithms by the stereo matching method. In this paper, we describe that the different method to acquiring 3 dimension fighting motion data and a HMM algorithm to recognize the data. One of the obtaining 3d data we used is depth map algorithm which is calculated by a stereo method. We test the 3d acquiring and the motion recognition system, and show the results of accuracy and performance results.