• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.396-398
• /
• 2011

본 논문은 두 대의 카메라와 한 대의 프로젝터로 구성된 Pro-cam시스템을 이용하여, 출력된 패턴 영상을 카메라로 촬영하고 이를 기반으로 Depth Map을 계산하는 모듈의 실시간 처리를 위한 GPU기반 병렬처리 기법을 제안한다. 입력받은 영상으로부터 구조광의 패턴을 해석하고, Depth Map을 계산하기 위해서, Dynamic pattern decoding하는 과정은 프로젝터의 패턴영상과 촬영된 카메라 패턴영상 간의 관계를 반복적으로 비교하므로, 이를 GPU 프로그래밍을 이용하여 병렬 처리를 통해 고속화하였다. 결과적으로 본 논문에서는 기존 CPU에서 수행했던 속도에 비해 약 18배정도 속도를 개선 할 수 있었다.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.4
• /
• pp.103-106
• /
• 2016

3D technology is main factor in Augmented Reality. Depth map is essential to make cubic effect using 2d image. There are a lot of ways to construct Depth map. Among them, stereo matching is mainly used. This paper presents how to generate depth map using stereo matching. For stereo matching, existing Dynamic programming method is used. To make accurate stereo matching, High-Boost Filter is applied to preprocessing method. As a result, when depth map is generated, accuracy based on Ground Truth soared.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.43-54
• /
• 2018

Images taken in haze weather are characteristic of low contrast and poor visibility. The process of reconstructing clear-weather image from a hazy image is called dehazing. The main challenge of image dehazing is to estimate the transmission map or depth map for an input hazy image. In this paper, we propose a single image dehazing method by utilizing the Generative Adversarial Network(GAN) for accurate depth map estimation. The proposed GAN model is trained to learn a nonlinear mapping between the input hazy image and corresponding depth map. With the trained model, first the depth map of the input hazy image is estimated and used to compute the transmission map. Then a guided filter is utilized to preserve the important edge information of the hazy image, thus obtaining a refined transmission map. Finally, the haze-free image is recovered via atmospheric scattering model. Although the proposed GAN model is trained on synthetic indoor images, it can be applied to real hazy images. The experimental results demonstrate that the proposed method achieves superior dehazing results against the state-of-the-art algorithms on both the real hazy images and the synthetic hazy images, in terms of quantitative performance and visual performance.

• Journal of information and communication convergence engineering
• /
• v.15 no.3
• /
• pp.193-198
• /
• 2017

In this study, we propose a three-dimensional (3D) visualization technique of occluded objects using integral imaging with a plenoptic camera. In previous studies, depth map estimation from elemental images was used to remove occlusion. However, the resolution of these depth maps is low. Thus, the occlusion removal accuracy is not efficient. Therefore, we use a plenoptic camera to obtain a high-resolution depth map. Hence, individual depth map for each elemental image can also be generated. Finally, we can regenerate a more accurate depth map for 3D objects with these separate depth maps, allowing us to remove the occlusion layers more efficiently. We perform optical experiments to prove our proposed technique. Moreover, we use MSE and PSNR as a performance metric to evaluate the quality of the reconstructed image. In conclusion, we enhance the visual quality of the reconstructed image after removing the occlusion layers using the plenoptic camera.

• Electronics and Telecommunications Trends
• /
• v.35 no.5
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.242-259
• /
• 2015

Three-dimensional video coding is one of the main challenges restricting the widespread applications of 3D video and free viewpoint video. In this paper, a novel fractal coding algorithm with motion-vector-field-based motion estimation for depth map sequence is proposed. We firstly add pre-search restriction to rule the improper domain blocks out of the matching search process so that the number of blocks involved in the search process can be restricted to a smaller size. Some improvements for motion estimation including initial search point prediction, threshold transition condition and early termination condition are made based on the feature of fractal coding. The motion-vector-field-based adaptive hexagon search algorithm on the basis of center-biased distribution characteristics of depth motion vector is proposed to accelerate the search. Experimental results show that the proposed algorithm can reach optimum levels of quality and save the coding time. The PSNR of synthesized view is increased by 0.56 dB with 36.97% bit rate decrease on average compared with H.264 Full Search. And the depth encoding time is saved by up to 66.47%. Moreover, the proposed fractal depth map sequence codec outperforms the recent alternative codecs by improving the H.264/AVC, especially in much bitrate saving and encoding time reduction.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.131-136
• /
• 1997

We present a method to estimate a dense and sharp depth map using multiple cameras for the application to flexible video production. A key issue for obtaining sharp depth map is how to overcome the harmful influence of occlusion. Thus, we first propose to selectively use the depth information from multiple cameras. With a simple sort and discard technique, we resolve the occlusion problem considerably at a slight sacrifice of noise tolerance. However, boundary overreach of more textured area to less textured area at object boundaries still remains to be solved. We observed that the amount of boundary overreach is less than half the size of the matching window and, unlike usual stereo matching, the boundary overreach with the proposed occlusion-overcoming method shows very abrupt transition. Based on these observations, we propose a hierarchical estimation scheme that attempts to reduce boundary overreach such that edges of the depth map coincide with object boundaries on the one hand, and to reduce noisy estimates due to insufficient size of matching window on the other hand. We show the hierarchical method can produce a sharp depth map for a variety of images.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.549-552
• /
• 2005

This paper presents a 3D video content generation technique and system that uses the multi-view images and the depth map. The proposed uses 3-view video and depth inputs from the 3-view video camera and depth camera for the 3D video content production. Each camera is calibrated using Tsai's calibration method, and its parameters are used to rectify multi-view images for the multi-view stereo matching. The depth and disparity maps for the center-view are obtained from both the depth camera and the multi-view stereo matching technique. These two maps are fused to obtain more reliable depth map. Obtained depth map is not only used to insert a virtual object to the scene based on the depth key, but is also used to synthesize virtual viewpoint images. Some preliminary test results are given to show the functionality of the proposed technique.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.877-891
• /
• 2018

In this paper, we propose a novel algorithm for rendering motion-blurred shadows utilizing a depth-time ranges shadow map. First, we render a scene from a light source to generate a shadow map. For each pixel in the shadow map, we store a list of depth-time ranges. Each range has two points defining a period where a particular geometry was visible to the light source and two distances from the light. Next, we render the scene from the camera to perform shadow tests. With the depths and times of each range, we can easily sample the shadow map at a particular receiver and time. Our algorithm runs entirely on GPUs and solves various problems encountered by previous approaches.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.492-500
• /
• 2012

In this paper, improved contour region coding method is proposed to accomplish better depth map coding performance. First of all, in order to use correlation between color video and depth map, a structure in SVC is applied to 3DVC. This can reduce bit-rate of the depth map while supporting the video to be transferred via various collection of network. As the depth map is mainly used to synthesize videos from different views, corrupted contour region can damage the overall quality of video. We hereby adapt a new differential quantization method when separating the contour region. The experimental results show that the proposed method can improve video quality by 0.06~0.5dB which translate the bit rate saving by 0.1~1.15%, when compared to the reference software.