• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.757-768
• /
• 2022

In this paper, we proposed a system that visualizes a hologram device in 3D by utilizing the CT image segmentation function based on artificial intelligence deep learning. The input axial CT medical image is converted into Sagittal and Coronal, and the input image and the converted image are divided into 3D volumes using ResUNet, a deep learning model. In addition, the volume is created by segmenting the tumor region in the segmented liver image. Each result is integrated into one 3D volume, displayed in a medical image viewer, and converted into a video. When the converted video is transmitted to the hologram device and output from the device, a 3D image with a sense of space can be checked. As for the performance of the deep learning model, in Axial, the basic input image, DSC showed 95.0% performance in liver region segmentation and 67.5% in liver tumor region segmentation. If the system is applied to a real-world care environment, additional physical contact is not required, making it safer for patients to explain changes before and after surgery more easily. In addition, it will provide medical staff with information on liver and liver tumors necessary for treatment or surgery in a three-dimensional manner, and help patients manage them after surgery by comparing and observing the liver before and after liver resection.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.2
• /
• pp.239-251
• /
• 2016

Hyperspectral image is widely used for land cover classification because it has a number of narrow bands and allow each pixel to include much more information in comparison with previous multi-spectral image. However, Higher spectral resolution of hyperspectral image results in an increase in data volumes and a decrease in noise efficiency. SAM(Spectral Angle Mapping), a method based on vector inner product to compare spectrum distribution, is a highly valuable and popular way to analyze continuous spectrum of hyperspectral image. SAM is shown to be less accurate when it is used to analyze hyperspectral image for land cover classification using spectral library. this inaccuracy is due to the effects of atmosphere. We suggest a decision tree based method to compensate the defect and show that the method improved accuracy of land cover classification.

• Ecology and Resilient Infrastructure
• /
• v.9 no.3
• /
• pp.154-162
• /
• 2022

In this study, a technique for estimating water surface velocity fields in the Universal Transverse Mercator coordinate system using the GPS information of a propagating drone but not ground control points is developed. First, we determine the image direction in which the upper side of an image is directed based on the navigation information of the drone. Subsequently, we assign the start and end frames of the video used and determine the analysis range. Using these two frames, we segment the measurement cross-section into a few subsections at regular intervals. At these subsections, we analyze 30 frame images to create spatio-temporal volumes for calculating the velocity fields. The results of the developed method (propagating drone surface image velocimetry) are compared with those of the existing method (hovering drone surface image velocimetry), and relatively good agreement is indicated between both in terms of the velocity fields.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.19-31
• /
• 2008

Video image processing systems(VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on wide-area detection, i.e., multi-lane surveillance algorithm provide traffic parameters with single camera such as flow and velocity, as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. The objective of this research was to relate traffic safety to VIPS tracking and this paper has developed a computer vision system of monitoring individual vehicle trajectories based on image processing, and offer the detailed information, for example, volumes, speed, and occupancy rate as well as traffic information via tripwire image detectors. Also the developed system has been verified by comparing with commercial VIP detectors.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.9-16
• /
• 2020

Recently, various studies are being conducted to integrate Image Segmentation into smart factory industries and autonomous driving fields. In particular, Image Segmentation systems using deep learning algorithms have been researched and developed enough to learn from large volumes of data with higher accuracy. In order to use image segmentation in the autonomous driving sector, sufficient amount of learning is needed with large amounts of data and the streaming environment that processes drivers' data in real time is important for the accuracy of safe operation through highways and child protection zones. Therefore, we proposed a novel DFCN algorithm that enhanced existing FCN algorithms that could be applied to various road environments, demonstrated that the performance of the DFCN algorithm improved 1.3% in terms of "loss" value compared to the previous FCN algorithms. Moreover, the proposed DFCN algorithm was applied to the existing U-Net algorithm to maintain the information of frequencies in the image to produce better results, resulting in a better performance than the classical FCN algorithm in the autonomous environment.

• Journal of Korea Water Resources Association
• /
• v.54 no.11
• /
• pp.933-942
• /
• 2021

The surface image velocimetry was developed to measure river flow velocity safely and effectively in flood season. There are a couple of methods in the surface image velocimetry. Among them the spatio-temporal image velocimetry is in the spotlight, since it can estimate mean velocity for a period of time. For the spatio-temporal image velocimetry analyzes a series of images all at once, it can reduce analyzing time so much. It, however, has a little drawback to find out the main flow direction. If the direction of spatio-temporal image does not coincide to the main flow direction, it may cause singnificant error in velocity. The present study aims to propose a new method to find out the main flow direction by using a fast Fourier transform(FFT) to a spatio-temporal (image) volume, which were constructed by accumulating the river surface images along the time direction. The method consists of two steps; the first step for finding main flow direction in space image and the second step for calculating the velocity magnitude in main flow direction in spatio-temporal image. In the first step a time-accumulated image was made from the spatio-temporal volume along the time direction. We analyzed this time-accumulated image by using FFT and figured out the main flow direction from the transformed image. Then a spatio-temporal image in main flow direction was extracted from the spatio-temporal volume. Once again, the spatio-temporal image was analyzed by FFT and velocity magnitudes were calculated from the transformed image. The proposed method was applied to a series of artificial images for error analysis. It was shown that the proposed method could analyze two-dimensional flow field with fairly good accuracy.

• Journal of Korean Society of Forest Science
• /
• v.80 no.3
• /
• pp.265-278
• /
• 1991

The purpose of this study is to suggest objective basic data for the design and management of the national park roadside slopes through the quantitative analysis of the visual quality included in the physical environment of the Chi-ri national park, for this, visual volumes of physical elements have been evaluated by using the mesh analysis, spatial images structure of physical elements have been analyzed by factor analysis algorithm, and degree of visual quality have been measured mainly by questionnaires. Result of this thesis can be summarized as fallows. Visual volumes of the naked, rock, ground cover of seed spray, and artificial planting are found to be the main factor determining the visual quality. Factors covering the spatial image of the national park roadside slopes landscape have been found to be the overall synthetic evaluation, spatial, appeal, physical, openness and dignity factors such as the overall the spatial, physical and openness yield high factor scores. As for the factors determining the degree of visual quality of the roadside slopes, variables such as the summit, the constructions management, harmony of landscape, visual stability of roadside slopes, suitable artificial planting and suitable constructions.

• Imaging Science in Dentistry
• /
• v.47 no.3
• /
• pp.165-174
• /
• 2017

Purpose: This study was performed to investigate the influence of object shape and distance from the center of the image on the volumetric accuracy of cone-beam computed tomography (CBCT) scans, according to different parameters of tube voltage and current. Materials and Methods: Four geometric objects(cylinder, cube, pyramid, and hexagon) with predefined dimensions were fabricated. The objects consisted of Teflon-perfluoroalkoxy embedded in a hydrocolloid matrix (Dupli-Coe-Loid TM; GC America Inc., Alsip, IL, USA), encased in an acrylic resin cylinder assembly. An Alphard Vega Dental CT system (Asahi Roentgen Ind. Co., Ltd, Kyoto, Japan) was used to acquire CBCT images. OnDemand 3D (CyberMed Inc., Seoul, Korea) software was used for object segmentation and image analysis. The accuracy was expressed by the volume error (VE). The VE was calculated under 3 different exposure settings. The measured volumes of the objects were compared to the true volumes for statistical analysis. Results: The mean VE ranged from -4.47% to 2.35%. There was no significant relationship between an object's shape and the VE. A significant correlation was found between the distance of the object to the center of the image and the VE. Tube voltage affected the volume measurements and the VE, but tube current did not. Conclusion: The evaluated CBCT device provided satisfactory volume measurements. To assess volume measurements, it might be sufficient to use serial scans with a high resolution, but a low dose. This information may provide useful guidance for assessing volume measurements.

• Korean Journal of Radiology
• /
• v.21 no.12
• /
• pp.1334-1344
• /
• 2020

Objective: Compressed sensing (CS) has gained wide interest since it accelerates MRI acquisition. We aimed to compare the 3D post-contrast T1-weighted volumetric isotropic turbo spin echo acquisition (VISTA) with CS (VISTA-CS) and without CS (VISTA-nonCS) in intracranial vessel wall MRIs (VW-MRI). Materials and Methods: From April 2017 to July 2018, 72 patients who underwent VW-MRI, including both VISTA-CS and VISTA-nonCS, were retrospectively enrolled. Wall and lumen volumes, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured from normal and lesion sites. Two neuroradiologists independently evaluated overall image quality and degree of normal and lesion wall delineation with a four-point scale (scores ≥ 3 defined as acceptable). Results: Scan coverage was increased in VISTA-CS to cover both anterior and posterior circulations with a slightly shorter scan time compared to VISTA-nonCS (approximately 7 minutes vs. 8 minutes). Wall and lumen volumes were not significantly different with VISTA-CS or VISTA-nonCS (interclass correlation coefficient = 0.964-0.997). SNR was or trended towards significantly higher values in VISTA-CS than in VISTA-nonCS. At normal sites, CNR was not significantly different between two sequences (p = 0.907), whereas VISTA-CS provided lower CNR in lesion sites compared with VISTA-nonCS (p = 0.003). Subjective wall delineation was superior with VISTA-nonCS than with VISTA-CS (p = 0.019), although overall image quality did not differ (p = 0.297). The proportions of images with acceptable quality were not significantly different between VISTA-CS (83.3-97.8%) and VISTA-nonCS (75-100%). Conclusion: CS may be useful for intracranial VW-MRI as it allows for larger scan coverage with slightly shorter scan time without compromising image quality.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.3_4
• /
• pp.195-203
• /
• 2004

VolumePro is a real-time volume rendering hardware for consumer PCs. However it cannot be used for the applications requiring perspective projection such as virtual endoscopy since it provides only orthographic projection. Several methods have been presented to approximate perspective projection by decomposing a volume into slabs and applying successive parallel projection to thou. But it takes a lot of time since the entire region of every slab should be processed, which does not contribute to final image. In this paper, we propose an efficient perspective projection method that makes the use of several sub-volumes with cropping feature of VolumePro. It reduces the rendering time in comparison to slab-based method without image quality deterioration since it processes only the parts contained in the view frustum.