• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.53-59
• /
• 2009

Multi-view video is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method by presentation of efficient layered depth image using real distance comparison, solution of overlap problem, and interpolation. In experimental results, confirmed high compression performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.818-819
• /
• 2014

Recently there are many works conducted on utilizing the DIBR (Depth-Image-Based Rendering) based intermediate images for the three-dimensional displays that do not require the use of stereoscopic glasses. However the prior works have used expensive depth cameras to obtain high-resolution depth images since DIBR-based intermediate image generation method requires the accuracy for depth information. In this study, we have developed the simulation to generate multi-view intermediate images based on the depth and color images using Microsoft Kinect. This simulation aims to support the acquisition of multi-view intermediate images utilizing the low-resolution depth and color image from Kinect, and provides the integrated service for the quality evaluation of the intermediate images. This paper describes the architecture and the system implementation of this simulation program.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.281-291
• /
• 2019

Depth from defocus estimates the 3D depth by using a phenomenon in which the object in the focal plane of the camera forms a clear image but the object away from the focal plane produces a blurred image. In this paper, algorithms are studied to estimate 3D depth by analyzing the degree of blur of the image taken with a single camera. The optimized object range was obtained by 3D depth estimation derived from depth from defocus using one image of a single camera or two images of different focus of a single camera. For depth estimation using one image, the best performance was achieved using a focal length of 250 mm for both smartphone and DSLR cameras. The depth estimation using two images showed the best 3D depth estimation range when the focal length was set to 150 mm and 250 mm for smartphone camera images and 200 mm and 300 mm for DSLR camera images.

• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.140-147
• /
• 2014

In this paper, we propose a method for real-time depth image refinement. In order to improve the quality of the depth map acquired from Kinect camera, we employ constant memory and texture memory which are suitable for a 2D image processing in the graphics processing unit (GPU). In addition, we applied the joint bilateral filter (JBF) in parallel to accelerate the overall execution. To enhance the quality of the depth image, we applied the JBF hierarchically using the compute unified device architecture (CUDA). Finally, we obtain the refined depth image. Experimental results showed that the proposed real-time depth image refinement algorithm improved the subjective quality of the depth image and the computational time was 260 frames per second.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.368-378
• /
• 2015

3D conversion technology has been studied over past decades and integrated to commercial 3D displays and 3DTVs. The 3D conversion plays an important role in the augmented functionality of three-dimensional television (3DTV), because it can easily provide 3D contents. Generally, depth cues extracted from a static image is used for generating a depth map followed by DIBR (Depth Image Based Rendering) rendering for producing a stereoscopic image. However except some particular images, the existence of depth cues is rare so that the consistent quality of a depth map cannot be accordingly guaranteed. Therefore, it is imperative to make a 3D conversion method that produces satisfactory and consistent 3D for diverse video contents. From this viewpoint, this paper proposes a novel method with applicability to general types of image. For this, saliency as well as edge is utilized. To generate a depth map, geometric perspective, affinity model and binomic filter are used. In the experiments, the proposed method was performed on 24 video clips with a variety of contents. From a subjective test for 3D perception and visual fatigue, satisfactory and comfortable viewing of 3D contents was validated.

• Journal of Korea Multimedia Society
• /
• v.18 no.2
• /
• pp.106-112
• /
• 2015

In this paper, we propose a method for correction of perspective distortion on a taken image. An image taken by a camera is caused perspective distortion depending on the direction of the camera when objects are projected onto the image. The proposed method in this paper is to obtain the normal vector of the plane through the depth information using a depth camera and calculate the direction of the camera based on this normal vector. Then the method corrects the perspective distortion to the view taken from the front side by performing a rotation transformation on the image according to the direction of the camera. Through the proposed method, it is possible to increase the processing speed than the conventional method such as correction of perspective distortion based on color information.

• Journal of information and communication convergence engineering
• /
• v.13 no.1
• /
• pp.62-68
• /
• 2015

In this paper, we propose a watermarking method for protecting the ownership of three-dimensional (3D) content generated from depth and texture images. After selecting the target areas to preserve the watermark by depth-image-based rendering, the reference viewpoint image is moved right and left in the depth map until the maximum viewpoint change is obtained and the overlapped region is generated for marking space. The region is divided into four subparts and scanned. After applying discrete cosine transform, the watermarks are inserted. To extract the watermark, the viewpoint can be changed by referring to the viewpoint image and the corresponding depth image initially, before returning to the original viewpoint. The watermark embedding and extracting algorithm are based on quantization. The watermarked image is attacked by the methods of JPEG compression, blurring, sharpening, and salt-pepper noise.

• Proceedings of the ESK Conference
• /
• 1995.04a
• /
• pp.181-186
• /
• 1995

This study investigated the effects of several factors - stimulus color, background color, and predicted depth - that affect depth perception in stereoscopic displays. For this study, two experiments were conducted; in the first experiment, the subjects were asked to indicate the depth perceived from presented image(rectangle) using matching mark, and in the second experiment, the subjects were asked to adjust one image(controllable rectangle) to have the same perceived depth as the other image(fixed rectangle) using keyboard. The depth perceived under various combination of levels of these factors was compared with depth predicted by the geometry of streopsis. Through two experiments, we found that stimulus color, predicted depth, and interaction between stimulus color and background color affected perceived depth significantly, and that red was perceived to be closest to the observer followed by yellow, green, and then blue.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.379-383
• /
• 2015

This paper presents an approach to detect object distance with the use of the recently developed low-cost Kinect sensor. The technique is based on Kinect color depth-image processing and can be used to design various computer-vision applications, such as object recognition, video surveillance, and autonomous path finding. The proposed technique uses keypoint feature detection in the Kinect depth image and advantages of depth pixels to directly obtain the feature distance in the depth images. This highly reduces the computational overhead and obtains the pixel distance in the Kinect captured images.