• 전자통신동향분석
• /
• 제35권5호
• /
• pp.112-122
• /
• 2020

In 3D computer graphics, a depth map is an image that provides information related to the distance from the viewpoint to the subject's surface. Stereo sensors, depth cameras, and imaging systems using an active illumination system and a time-resolved detector can perform accurate depth measurements with their own light sources. The 3D image information obtained through the depth map is useful in 3D modeling, autonomous vehicle navigation, object recognition and remote gesture detection, resolution-enhanced medical images, aviation and defense technology, and robotics. In addition, the depth map information is important data used for extracting and restoring multi-view images, and extracting phase information required for digital hologram synthesis. This study is oriented toward a recent research trend in deep learning-based 3D data analysis methods and depth map information extraction technology using a convolutional neural network. Further, the study focuses on 3D image processing technology related to digital hologram and multi-view image extraction/reconstruction, which are becoming more popular as the computing power of hardware rapidly increases.

• 방송공학회논문지
• /
• 제20권3호
• /
• pp.368-378
• /
• 2015

2D영상의 3D변환 기술은 3D 디스플레이 및 3DTV에 기본적으로 장착된 기술로 꾸준히 연구 및 상업화가 진행된 기술이다. 이 기술은 3D 입체영상 콘텐츠 부족을 해결할 수 있다는 장점이 있다. 3D변환은 정지영상으로부터 다양한 깊이단서를 이용하여 깊이맵을 추출한 후에, DIBR(Depth Image Based Rendering)로 입체영상을 생성한다. 특정 영상이외에는 영상에서 신뢰성 있는 단서가 있는 경우는 많지 않다. 따라서 3D변환 기술은 일반 영상에서도 우수하고, 일관된 입체영상이 생성하는 것이 중요하다. 이러한 관점에서 본논문에서는 상기 조건을 만족할 수 있는 3D변환 방법을 제안한다. 주 기술로 최근 다양한 분야에서 활용되는 관심맵과 에지를 활용한 다. 깊이맵을 생성하기 위해서 기하적 투영, 근접 모델 및 바이노믹 필터를 활용한다. 실험에서는 제안한 방법을 24개의 2D 비디오 콘텐츠에 적용하였고, 입체감 및 시각적 피로도 등의 주관적 평가를 통해 3D 콘텐츠의 우수한 만족도를 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제22권5호
• /
• pp.547-557
• /
• 2019

To extract the depth map from a single image, a number of CNN-based deep learning methods have been performed in recent research. In this study, the GAN structure of Pix2Pix is maintained. this model allows to converge well, because it has the structure of the generator and the discriminator. But the convolution in this model takes a long time to compute. So we change the convolution form in the generator to a depthwise convolution to improve the speed while preserving the result. Thus, the seven down-sizing convolutional hidden layers in the generator U-Net are changed to depthwise convolution. This type of convolution decreases the number of parameters, and also speeds up computation time. The proposed model shows similar depth map prediction results as in the case of the existing structure, and the computation time in case of a inference is decreased by 64%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• 방송공학회논문지
• /
• 제13권5호
• /
• pp.596-601
• /
• 2008

본 논문은 저해상도의 깊이 카메라와 고해상도의 양안식 카메라를 결합한 복합형 카메라 시스템에서 관심영역(region of interest, ROI)이 향상된 깊이맵을 생성하는 새로운 방법을 제안한다. 제안하는 방법은 깊이 카메라로 획득한 깊이 정보를 3차원 워핑(warping)하여 좌영상의 ROI 깊이맵을 생성한다. 그런 다음, 양안식 카메라로 획득한 좌우영상의 배경 영역을 스테레오 정합하여 좌영상의 배경 깊이맵을 생성한다. 최종적으로, ROI 깊이맵과 배경 깊이맵을 결합하여 최종 깊이맵을 생성한다. 제안하는 방법으로 생성한 고해상도 깊이맵은 기존의 스테레오 정합 방법보다 ROI에 정확한 깊이 정보를 제공한다.

• Ocean Systems Engineering
• /
• 제11권4호
• /
• pp.331-351
• /
• 2021

Underwater images are very much different from images taken on land, due to the presence of a higher disturbance ratio caused by the presence of water medium between the camera and the target object. These distortions and noises result in unclear details and reduced quality of the output image. An underwater image restoration method is proposed in this paper, which uses blurriness information, background light neutralization information, and red-light intensity to estimate depth. The transmission map is then estimated using the derived depth map, by considering separate attenuation coefficients for direct and backscattered signals. The estimated transmission map and estimated background light are then used to recover the scene radiance. Qualitative and quantitative analysis have been used to compare the performance of the proposed method against other state-of-the-art restoration methods. It has been shown that the proposed method can yield good quality restored underwater images. The proposed method has also been evaluated using different qualitative metrics, and results have shown that method is highly capable of restoring underwater images with different conditions. The results are significant and show the applicability of the proposed method for underwater image restoration work.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.28-30
• /
• 2009

This paper describes a 3-DTIP(3-D Tour Into Picture) using depth map for a Korean classical painting being composed of persons and landscape. Unlike conventional TIP methods providing 2-D image or video, our proposed TIP can provide users with 3-D stereoscopic contents. Navigating inside a picture provides more realistic and immersive perception. The method firstly makes depth map. Input data consists of foreground object, background image, depth map, foreground mask. Firstly we separate foreground object and background, make each of their depth map. Background is decomposed into polygons and assigned depth value to each vertexes. Then a polygon is decomposed into many triangles. Gouraud shading is used to make a final depth map. Navigating into a picture uses OpenGL library. Our proposed method was tested on "Danopungjun" and "Muyigido" that are famous paintings made in Chosun Dynasty. The stereoscopic video was proved to deliver new 3-D perception better than 2-D video.

• 한국통신학회논문지
• /
• 제36권12C호
• /
• pp.738-743
• /
• 2011

고해상도 3차원 깊이 영상은 고품질의 3차원 방송을 위해 필요한 중요한 정보이다. 깊이 카메라는 정확한 깊이 정보를 실시간으로 얻을 수 있지만, 카메라 물리적 한계로 인해 저해상도의 깊이 영상만 이용한다. 본 논문에서는 저해상도의 깊이 영상과 색상 영상을 이용하여 색상 영상을 보간 하는 방법을 제안한다. 제안하는 방법은 랜덤워크 확률 모델을 이용하여 각 화소들이 초기 깊이값과 같을 확률값을 정의하여 가장 높은 확률을 가지는 초기 깊이값을 나머지 화소들에 복사한다. 제안한 방법은 인접한 화소들만을 이용하는 것이 아니라 경로를 따라 비용을 계산함으로써, 여러 화소에 걸친 색상의 변화율이 고려되어 물체의 경계 주변에서 색상 영역과 깊이 영상간의 경계가 일치하는 향상된 깊이 영상을 얻을 수 있다.

• 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).

• 방송공학회논문지
• /
• 제16권6호
• /
• pp.916-926
• /
• 2011

3D 영화 콘텐츠처럼 고해상도로 만들어진 입체영상은 저해상도 영상에서는 동일한 3D 깊이감을 느낄 수가 없다는 단점이 있다. 본 논문에서는 공간적 복잡도을 이용하여 깊이맵을 변환하여 입체감을 개선할 수 있는 방법을 제안한다. 제안 방법에서는 깊이맵의 히스토그램을 분석한 후에, 깊이맵을 다수의 깊이평면으로 분할한 다음에 깊이 평면을 변환한다. 마지막으로 변환된 깊이평면을 통합하여 최종 깊이맵을 생성한다. 주관적 평가 실험에서는 입체감 개선 및 이에 따라 발생하는 시각적 피로도를 검증하였다. 실험에서는 입체감의 개선이 증명되었으며, 영상 해상도가 낮아져도, 입체감은 유지되는 것을 보여주었다. 또한 얻어진 입체영상의 시각적 피로도 검증을 통해서 생성된 입체영상은 피로도가 증가하지 않는 것을 보여주었다.