• Imaging Science in Dentistry
• /
• v.32 no.4
• /
• pp.201-206
• /
• 2002

Purpose : To evaluate the radiographic change of operation sites after orthognathic surgery using the digital image processing and fractal analysis. Materials and Methods : A series of panoramic radiographs of thirty-five randomly selected patients who had undergone mandibular orthognathic surgery (bilateral sagittal split ramus osteotomy) without clinical complication for osseous healing, were taken. The panoramic radiographs of each selected patient were taken at pre-operation (stage 0), 1 or 2 days after operation (stage 1), 1 month after operation (stage 2), 6 months after operation (stage 3), and 12 months after operation (stage 4). The radiographs were digitized at 600 dpi, 8 bit, and 256 gray levels. The region of interest, centered on the bony gap area of the operation site, was selected and the fractal dimension was calculated by using the tile-counting method. The mean values and standard deviations of fractal dimension for each stage were calculated and the differences among stage 0, 1, 2, 3, and 4 were evaluated through repeated measures of the ANOVA and paired t-test. Results : The mean values and standard deviations of the fractal dimensions obtained from stage 0, 1, 2, 3, and 4 were 1.658±0.048, 1.580±0.050, 1.607±0.046, 1.624±0.049, and 1.641 ±0.061, respectively. The fractal dimensions from stage 1 to stage 4 were shown to have a tendency to increase (p < 0.05). Conclusion: The tendency of the fractal dimesion to increase relative to healing time may be a useful means of evaluating post-operative bony healing of the osteotomy site.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.561-566
• /
• 2003

This paper proposes a new algorithm that generates smooth and realistic transition views from one viewpoint to another view point on the panorama based navigation system. The proposed algorithm is composed with two steps. One is prewarping that aligns the viewing direction in two panorama image, the other is bidirectional disparity morphing (BDM) that generates the intermediate scene from the aligned panorama images. For the prewarping, first of all, we compute the phase correlation between two images in order to get the information such as the displacement, rotation, and scale. Then we align the original images using these information. As soon as finishing the prewarping, we compute the block based disparity vectors (DVs) and smooth them using the two occluding patterns. As we apply these DVs to the BDM, we can get the elaborate intermediate scenes. We make an experiment on the proposed algorithm with real panoramic images and we can get the satisfactory results.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.760-763
• /
• 2006

In this paper, a small portion of coastline on the EAST SEA was studied using CORONA panoramic satellite photo and 1:5000 Korean National Topographic Map. The project site near Kangneung city was 3 Km shoreline on the Kangmoon Beach and the SongJeong Beach, which have suffered from severe erosion. The first and the most important step was to rectify a CORONA image over the project site. A rigid mathematical model and a heuristic polynomial transformation were used for the purpose. The rectified image was overlaid with 1:5000 Korean National Topographic Map produced by aerial mapping. Among numerous methods for shoreline erosion measurement, area-based approach was chosen and used for the computation for annual shoreline recession. The final result of the analysis was that the average recession in the period of 1963-1998 was 33.6m and the annual rate was 0.96m.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.167.6-167
• /
• 2001

The cylindrical environment maps of image-based representation methods make high-quality, simple and low-price real-time navigation possible. In this paper, we propose a method to navigate from one viewpoint to the next in the virtual inside space, composed of several cylindrical environment maps. Our system is classified into the two modules. first of all, the panoramic image viewer that employs the rotation and zoom-in/out methods to navigate the virtual inside space, such as the Quicklime VR. The other is smooth real-time navigation using cubic mesh interpolation when the viewpoint moves from one environment map to another in the virtual space.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.665-668
• /
• 2002

본 논문은 카메라를 수평이동시켜 얻어진 영상을 Mellin Transform을 이용하여 파노라마 이미지를 구성하는 방법을 제안한다. 일반적으로 카메라로부터 얻어진 동영상은 각 프레임 사이에 많은 시간적, 공간적 정보가 중복되어 있다. 이러한 중복 정보는 모자이크 방법 중의 하나인 파노라믹 기법을 사용하여 줄일 수 있다. 지금까지의 제안된 이미지의 중복성을 찾는 알고리즘들은 노이즈에 지나치게 민감하거나 중복성을 계산하는 데 있어 시간이 많이 소모되는 단점이 있었다. 따라서 본 논문에서는 Mellin Transform 을 사용하여 노이즈에 덜 민감하고 빠른 시간에 이미지의 중복 정보를 찾아내는 방법을 제안한다. Mellin Transform을 이용하여 생성된 파노라마 영상은 이미지의 이동정보를 쉽게 구할 있어 동영상에서 움직이는 물체를 추적하거나 추정이 가능하여 물체 tracking 영역에 응용될 수 있을 것으로 보이며 또한 앞으로 현실감 있는 가상현실의 배경 생성에 도움이 될 것으로 생각된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1468-1471
• /
• 2012

It is always a dream to recreate the experience of a particular place, the Panorama Virtual Reality has been interpreted as a kind of technology to create virtual environments and the ability to maneuver angle for and select the path of view in a dynamic scene. In this paper we examined an efficient algorithm for Image registration and stitching of captured imaged from a video stream. Two approaches are studied in this paper. First, dynamic programming is used to spot the ideal key points, match these points to merge adjacent images together, later image blending is use for smooth color transitions. In second approach, FAST and SURF detection are used to find distinct features in the images and a nearest neighbor algorithm is used to match corresponding features, estimate homography with matched key points using RANSAC. The paper also covers the automatically choosing (recognizing, comparing) images to stitching method.

• Imaging Science in Dentistry
• /
• v.46 no.3
• /
• pp.203-210
• /
• 2016

Purpose: The purpose of this study was to investigate appropriate contrast reference values (CRVs) by comparing the contrast in phantom and clinical images. Materials and Methods: Phantom contrast was measured using two methods: (1) counting the number of visible pits of different depths in an aluminum plate, and (2) obtaining the contrast-to-noise ratio (CNR) for 5 tissue-equivalent materials (porcelain, aluminum, polytetrafluoroethylene [PTFE], polyoxymethylene [POM], and polymethylmethacrylate [PMMA]). Four panoramic radiographs of the contrast phantom, embedded in the 4 different regions of the arch-form stand, and 1 real skull phantom image were obtained, post-processed, and compared. The clinical image quality evaluation chart was used to obtain the cut-off values of the phantom CRV corresponding to the criterion of being adequate for diagnosis. Results: The CRVs were obtained using 4 aluminum pits in the incisor and premolar region, 5 aluminum pits in the molar region, and 2 aluminum pits in the temporomandibular joint (TMJ) region. The CRVs obtained based on the CNR measured in the anterior region were: porcelain, 13.95; aluminum, 9.68; PTFE, 6.71; and POM, 1.79. The corresponding values in the premolar region were: porcelain, 14.22; aluminum, 8.82; PTFE, 5.95; and POM, 2.30. In the molar region, the following values were obtained: porcelain, 7.40; aluminum, 3.68; PTFE, 1.27; and POM, - 0.18. The CRVs for the TMJ region were: porcelain, 3.60; aluminum, 2.04; PTFE, 0.48; and POM, - 0.43. Conclusion: CRVs were determined for each part of the jaw using the CNR value and the number of pits observed in phantom images.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.20-30
• /
• 2022

Recently, as VR (Virtual Reality) technology has been in the spotlight, 360° panoramic images that can view lively VR contents are attracting a lot of attention. Image stitching technology is a major technology for producing 360° panorama images, and many studies are being actively conducted. Typical stitching algorithms are based on feature point-based image stitching. However, conventional feature point-based image stitching methods have a problem that stitching results are intensely affected by feature points. To solve this problem, deep learning-based image stitching technologies have recently been studied, but there are still many problems when there are few overlapping areas between images or large parallax. In addition, there is a limit to complete supervised learning because labeled ground-truth panorama images cannot be obtained in a real environment. Therefore, we produced three fisheye images with different camera centers and corresponding ground truth image through carla simulator that is widely used in the autonomous driving field. We propose image stitching model that creates a 360° panorama image with the produced fisheye image. The final experimental results are virtual datasets configured similar to the actual environment, verifying stitching results that are strong against various environments and large parallax.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.1
• /
• pp.70-77
• /
• 2014

This paper proposes a novel localization algorithm based on ego-motion which used Lucas-Kanade Optical Flow and warping image obtained through fish-eye lenses mounted on the robots. The omnidirectional image sensor is a desirable sensor for real-time view-based recognition of a robot because the all information around the robot can be obtained simultaneously. The preprocessing (distortion correction, image merge, etc.) of the omnidirectional image which obtained by camera using reflect in mirror or by connection of multiple camera images is essential because it is difficult to obtain information from the original image. The core of the proposed algorithm may be summarized as follows: First, we capture instantaneous $360^{\circ}$ panoramic images around a robot through fish-eye lenses which are mounted in the bottom direction. Second, we extract motion vectors using Lucas-Kanade Optical Flow in preprocessed image. Third, we estimate the robot position and angle using ego-motion method which used direction of vector and vanishing point obtained by RANSAC. We confirmed the reliability of localization algorithm using ego-motion based on fisheye warping image through comparison between results (position and angle) of the experiment obtained using the proposed algorithm and results of the experiment measured from Global Vision Localization System.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.487-498
• /
• 2022

Depth map is an image that contains distance information in 3D space on a 2D plane and is used in various 3D vision tasks. Many existing depth estimation studies mainly use narrow FoV images, in which a significant portion of the entire scene is lost. In this paper, we propose a technique for generating 360° omnidirectional RGBD images from a sparse set of narrow FoV images. The proposed generative adversarial network based image generation model estimates the relative FoV for the entire panoramic image from a small number of non-overlapping images and produces a 360° RGB and depth image simultaneously. In addition, it shows improved performance by configuring a network reflecting the spherical characteristics of the 360° image.