• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.549-556
• /
• 2001

The general problems of recovering 3D for 2D imagery require the depth information for each picture element form focus. The manual creation of those 3D models is consuming time and cost expensive. The goal in this paper is to simplify the depth estimation algorithm that extracts the depth information of every region from monocular image sequence with camera translation to implement 3D video in realtime. The paper is based on the property that the motion of every point within image which taken from camera translation depends on the depth information. Full-search motion estimation based on block matching algorithm is exploited at first step and ten, motion vectors are compensated for the effect by camera rotation and zooming. We have introduced the algorithm that estimates motion of object by analysis of monocular motion picture and also calculates the averages of frame depth and relative depth of region to the average depth. Simulation results show that the depth of region belongs to a near object or a distant object is in accord with relative depth that human visual system recognizes.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.275-278
• /
• 2012

본 논문에서 2D-3D 자동 영상 변환을 위하여 2D 상으로부터 깊이 지도(depth map)을 생성하는 방법을 제안한다. 제안하는 방법은 보다 정확한 깊이 지도 생성을 위해 영상의 전경 깊이 지도(foreground depth map)와 배경 깊이 지도(background depth map)를 각각 생성 한 후 결합함으로써 보다 정확한 깊이 지도를 생성한다. 먼저, 전경 깊이 지도를 생성하기 위해서 라플라시안 피라미드(laplacian pyramid)를 이용하여 포커스/디포커스 깊이 지도(focus/defocus depth map)를 생성한다. 그리고 블록정합(block matching)을 통해 획득한 움직임 시차(motion parallax)를 이용하여 움직임 시차 깊이 지도를 생성한다. 포커스/디포커스 깊이 지도는 평탄영역(homogeneous region)에서 깊이 정보를 추출하지 못하고, 움직임 시차 깊이 지도는 움직임 시차가 발생하지 않는 영상에서 깊이 정보를 추출하지 못한다. 이들 깊이 지도를 결합함으로써 각 깊이 지도가 가지는 문제점을 해결하였다. 선형 원근감(linear perspective)와 선 추적(line tracing) 방법을 적용하여 배경깊이 지도를 생성한다. 이렇게 생성된 전경 깊이 지도와 배경 깊이 지도를 결합하여 보다 정확한 깊이 지도를 생성한다. 실험 결과, 제안하는 방법은 기존의 방법들에 비해 더 정확한 깊이 지도를 생성하는 것을 확인할 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.13-18
• /
• 2011

In this paper, we explain capturing, postprocessing, and depth generation methods using multiple color and depth cameras. Although the time-of-flight (TOF) depth camera measures the scene's depth in real-time, there are noises and lens distortion in the output depth images. The correlation between the multi-view color images and depth images is also low. Therefore, it is essential to correct the depth images and then we use them to generate the depth information of the scene. The results of stereo matching based on the disparity information from the depth cameras showed the better performance than the previous method. Moreover, we obtained the accurate depth information even at the occluded or textureless regions which are the weaknesses of stereo matching.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.451-453
• /
• 2012

2D영상을 3D영상으로 변환하기 위해서는 영상 내의 깊이 정보를 알 수 있는 깊이지도(depth map)가 필요하다. 깊이지도를 획득하기 위해 다양한 시각적 특성들이 이용되는데, 본 논문에서는 영상에서 아래는 가깝고 위는 멀다는 가정을 기반으로 하는 상대적 높이(relative height) 특성을 이용하여 깊이지도를 생성하는 방법을 제안한다. 기존의 상대적 높이 특성을 이용한 방법들은 왼쪽이나 오른쪽으로 거리가 멀어지는 영상에 대해서 부정확한 깊이지도를 생성한다. 따라서 제안하는 방법에서는 문제점을 개선하기 위해 입력 영상을 소실점 위치에 따라 분류하여 깊이지도를 생성한다. 소실점이 왼쪽이나 오른쪽에 위치할 때는 영상을 회전시켜 소실점을 상단으로 보내 상대적 높이 가정에 맞도록 영상을 변환하고 소실점이 중앙에 위치할 때는 하늘 검출 방법을 통해 실내, 실외를 판별한 후 각 특성에 맞는 초기 깊이 모델을 적용한다. 실험 결과, 제안하는 방법이 상대적 높이 가정을 만족하지 않는 영상도 적합한 깊이지도를 생성할 수 있음을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.431-438
• /
• 2016

In this paper, we present an upsampling technique for depth map image using color and depth weights. First, we construct a high-resolution image using the bilinear interpolation technique. Next, we detect a common edge region using RGB color space, HSV color space, and depth image. If an interpolated pixel belongs to the common edge region, we calculate weighting values of color and depth in $3{\times}3$ neighboring pixels and compute the cost value to determine the boundary pixel value. Finally, the pixel value having minimum cost is determined as the pixel value of the high-resolution depth image. Simulation results show that the proposed algorithm achieves good performance in terns of PSNR comparison and subjective visual quality.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.6
• /
• pp.23-29
• /
• 2016

In this paper, we propose a method of depth video coding to find the closest sphere through the depth information when the spherical object is captured. We find the closest sphere to the captured spherical object using method of least squares in each block. Then, we estimate the depth value through the found sphere and encode the depth video through difference between the measured depth values and the estimated depth values. Also, we encode factors of the estimated sphere with encoded pixels within the block. The proposed method improves the coding efficiency up to 81% compared to the conventional DPCM method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.617-624
• /
• 2004

This paper describes a new facial feature localization method that uses Adjacent Depth Differences(ADD) in 3D facial surface. In general, human recognize the extent of deepness or shallowness of region relatively, in depth, by comparing the neighboring depth information among regions of an object. The larger the depth difference between regions shows, the easier one can recognize each region. Using this principal, facial feature extraction will be easier, more reliable and speedy. 3D range images are used as input images. And ADD are obtained by differencing two range values, which are separated at a distance coordinate, both in horizontal and vertical directions. ADD and input image are analyzed to extract facial features, then localized a nose region, which is the most prominent feature in 3D facial surface, effectively and accurately.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.14-17
• /
• 2020

단안 영상에서의 깊이 추정은 주어진 시점에서 촬영된 2 차원 영상으로부터 객체까지의 3 차원 거리 정보를 추정하는 것이다. 최근 딥러닝 기반으로 단안 RGB 영상에서 깊이 정보 추정에 유용한 특징 맵을 추출하고 이를 이용해서 깊이를 추정하는 모델들이 기존 방법들의 성능을 넘어서면서 관련된 연구가 활발히 진행되고 있다. 또한 Attention Model 과 같이 특정 특징 맵의 채널 혹은 공간을 강조하여 전체적인 네트워크의 성능을 개선하는 연구가 소개되었다. 본 논문에서는 깊이 정보 추정을 위해 사용되는 특징 맵을 강조하기 위해서 Attention Model 을 추가한 AutoEncoder 기반의 깊이 추정 네트워크를 제안하고 적용 부분에 따른 네트워크의 깊이 정보 추정 성능을 평가 및 분석한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12C
• /
• pp.1147-1153
• /
• 2009

We propose a novel image segmentation and segment-based stereo matching technique using color, depth, and motion information. Proposed technique firstly splits reference images into foreground region or background region using depth information from depth camera. Then each region is segmented into small segments with color information. Moreover, extracted segments in current frame are tracked in the next frame in order to maintain depth consistency between frames. The initial depth from the depth camera is also used to set the depth search range for stereo matching. Proposed segment-based stereo matching technique was compared with conventional one without foreground and background separation and other conventional one without motion tracking of segments. Simulation results showed that the improvement of segment extraction and depth estimation consistencies by proposed technique compared to conventional ones especially at the static background region.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.243-248
• /
• 2013

In this paper, depth of foreground is analysed by focus and color analysis grouping for 2D/3D video conversion and depth of foreground progressing method is preposed by using focus and motion information. Candidate foreground image is generated by estimated movement of image focus information for extracting foreground from 2D video. Area of foreground is extracted by filling progress using color analysis on hole area of inner object existing candidate foreground image. Depth information is generated by analysing value of focus existing on actual frame for allocating depth at generated foreground area. Depth information is allocated by weighting motion information. Results of previous proposed algorithm is compared with proposed method from this paper for evaluating the quality of generated depth information.