• Geomechanics and Engineering
• /
• v.36 no.3
• /
• pp.205-215
• /
• 2024

Manually mapping fractures in construction stone mines is challenging, time-consuming, and hazardous. In this method, there is no physical access to all points. In contrast, digital image processing offers a safe, cost-effective, and fast alternative, with the capability to map all joints. In this study, two methods of detecting the trace of discontinuities using image processing in construction stone mines are presented. To achieve this, we employ two modified Hough transform algorithms and the degree of neighborhood technique. Initially, we introduced a method for selecting the best edge detector and smoothing algorithms. Subsequently, the Canny detector and median smoother were identified as the most efficient tools. To trace discontinuities using the mentioned methods, common preprocessing steps were initially applied to the image. Following this, each of the two algorithms followed a distinct approach. The Hough transform algorithm was first applied to the image, and the traces were represented through line drawings. Subsequently, the Hough transform results were refined using fuzzy clustering and reduced clustering algorithms, along with a novel algorithm known as the farthest points' algorithm. Additionally, we developed another algorithm, the degree of neighborhood, tailored for detecting discontinuity traces in construction stones. After completing the common preprocessing steps, the thinning operation was performed on the target image, and the degree of neighborhood for lineament pixels was determined. Subsequently, short lines were removed, and the discontinuities were determined based on the degree of neighborhood. In the final step, we connected lines that were previously separated using the method to be described. The comparison of results demonstrates that image processing is a suitable tool for identifying rock mass discontinuity traces. Finally, a comparison of two images from different construction stone mines presented at the end of this study reveals that in images with fewer traces of discontinuities and a softer texture, both algorithms effectively detect the discontinuity traces.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.4
• /
• pp.63-75
• /
• 2016

Aquaculture has historically delivered marine products because the country is surrounded by ocean on three sides. Surveys on production have been conducted recently to systematically manage aquaculture facilities. Based on survey results, pricing controls on marine products has been implemented to stabilize local fishery resources and to ensure minimum income for fishermen. Such surveys on aquaculture facilities depend on manual digitization of aerial photographs each year. These surveys that incorporate manual digitization using high-resolution aerial photographs can accurately evaluate aquaculture with the knowledge of experts, who are aware of each aquaculture facility's characteristics and deployment of those facilities. However, using aerial photographs has monetary and time limitations for monitoring aquaculture resources with different life cycles, and also requires a number of experts. Therefore, in this study, we investigated an automatic prototype system for detecting boundary information and monitoring aquaculture facilities based on satellite images. KOMPSAT-3 (13 Scene), a local high-resolution satellite provided the satellite imagery collected between October and April, a time period in which many aquaculture facilities were operating. The ANN classification method was used for automatic detecting such as cage, longline and buoy type. Furthermore, shape files were generated using a digitizing image processing method that incorporates polygon generation techniques. In this study, our newly developed prototype method detected aquaculture facilities at a rate of 93%. The suggested method overcomes the limits of existing monitoring method using aerial photographs, but also assists experts in detecting aquaculture facilities. Aquaculture facility detection systems must be developed in the future through application of image processing techniques and classification of aquaculture facilities. Such systems will assist in related decision-making through aquaculture facility monitoring.

• Journal of Korean Society of Transportation
• /
• v.29 no.5
• /
• pp.121-138
• /
• 2011

More affordable and available cutting-edge technologies (e.g., wireless vehicle communication) are regarded as a possible alternative to the fixed infrastructure-based traffic information system requiring the expensive infrastructure investments and mostly implemented in the uninterrupted freeway network with limited spatial system expansion. This paper develops an advanced decentralized traveler information System (ATIS) using vehicle-to-vehicle (V2V) communication system whose performance (drivers' travel time savings) are enhanced by three complementary functions (autonomous automatic incident detection algorithm, reliable sample size function, and driver behavior model) and evaluates it in the typical $6{\times}6$ urban grid network with non-recurrent traffic state (traffic incident) with the varying key parameters (traffic flow, communication radio range, and penetration ratio), employing the off-the-shelf microscopic simulation model (VISSIM) under the ideal vehicle communication environment. Simulation outputs indicate that as the three key parameters are increased more participating vehicles are involved for traffic data propagation in the less communication groups at the faster data dissemination speed. Also, participating vehicles saved their travel time by dynamically updating the up-to-date traffic states and searching for the new route. Focusing on the travel time difference of (instant) re-routing vehicles, lower traffic flow cases saved more time than higher traffic flow ones. This is because a relatively small number of vehicles in 300vph case re-route during the most system-efficient time period (the early time of the traffic incident) but more vehicles in 514vph case re-route during less system-efficient time period, even after the incident is resolved. Also, normally re-routings on the network-entering links saved more travel time than any other places inside the network except the case where the direct effect of traffic incident triggers vehicle re-routings during the effective incident time period and the location and direction of the incident link determines the spatial distribution of re-routing vehicles.

• Progress in Medical Physics
• /
• v.24 no.2
• /
• pp.99-107
• /
• 2013

The surgical resection was occurred mainly in liver metastasis before the development of radiation therapy techniques. Recently, Radiation therapy is increased gradually due to the development of radiation dose delivery techniques. 18F-FDG PET image showed better sensitivity and specificity in liver metastasis detection. This image modality is important in the radiation treatment with planning CT for tumor delineation. In this study, we applied automatic image segmentation methods on PET image of liver metastasis and examined the impact of image factors on these methods. We selected the patients who were received the radiation therapy and 18F-FDG PET/CT in Korea Cancer Center Hospital from 2009 to 2012. Then, three kinds of image segmentation methods had been applied; The relative threshold method, the Gradient method and the region growing method. Based on these results, we performed statistical analysis in two directions. 1. comparison of GTV and image segmentation results. 2. performance of regression analysis for relation between image factor affecting image segmentation techniques. The mean volume of GTV was $60.9{\pm}65.9$ cc and the $GTV_{40%}$ was $22.43{\pm}35.27$ cc, and the $GTV_{50%}$ was $10.11{\pm}17.92$ cc, the $GTV_{RG}$ was $32.89{\pm}36.8$4 cc, the $GTV_{GD}$ was $30.34{\pm}35.77$ cc, respectively. The most similar segmentation method with the GTV result was the region growing method. For the quantitative analysis of the image factors which influenced on the region growing method, we used the standardized coefficient ${\beta}$, factors affecting the region growing method show GTV, $TumorSUV_{MAX/MIN}$, $SUV_{max}$, TBR in order. The result of the region growing (automatic segmentation) method showed the most similar result with the CT based GTV and the region growing method was affected by image factors. If we define the tumor volume by the auto image segmentation method which reflect the PET image parameters, more accurate and consistent tumor contouring can be done. And we can irradiate the optimized radiation dose to the cancer, ultimately.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.652-657
• /
• 2018

Breeding control in a farm is a very important factor affecting milk productivity. Breeding management is important for the early detection of estrus, and reliable, automatic, more accurate, and faster monitoring of the timing of dairy cows is essential for farmers. This study measured the accuracy of estrus using the estrus indications, changes in activities, rumination activities, ruminal temperature, and pH. The biomedical information device S1 used in this study provided an estrus notice using the rumen temperature, pH, cow activities, and number of drinking estimations, which were inserted in the rumen through the oral route. The S2 device was used in the estrus notice for the rumen activities and cow activities. The data collected on the instrument were collected at intervals of 2 hours per day at the reference days (RD: -7~-3, +7~+ 3) +2), 7 days before insemination, and 7 days after insemination. The activities of the S1 device used in this paper increased with increasing number of insemination days (-1: $12.5{\pm}1.03/day$; 0: $12.9{\pm}1.73/day$) compared to the reference day (RD: $10.2{\pm}1.0/day$). The activities of the S2 device was also found to increase from the reference day to the insemination day (0: $63.0{\pm}3.66$) compared to the reference day (RD: $40.3{\pm}2.68$). The number of daily drinks in S1 decreased from the reference day (RD: $5.9{\pm}0.89/day$) to before the insemination day (-2: $5.6{\pm}0.98$; -1: $5.7{\pm}0.96$); +2: $6.0{\pm}0.73$). The number of daily drinks on the insemination day (0: $6.3{\pm}0.86$; +2: $6.0{\pm}0.73$) was similar to the reference day. The number of daily rumination in S2 decreased from the reference day (RD: $493.8{\pm}10.92$) to the insemination day (-1: $390.2{\pm}13.36$; 0: $354.1{\pm}16.71$).

• Journal of Astronomy and Space Sciences
• /
• v.22 no.4
• /
• pp.393-408
• /
• 2005

We developed and compared two automatic algorithms for moving object detections in the YSTAR-NEOPAT sky survey program. One method, called starlist comparison method, is to identify moving object candidates by comparing the photometry data tables from successive images. Another method, called image subtraction method, is to identify the candidates by subtracting one image from another which isolates sources moving against background stars. The efficiency and accuracy of these algorithms have been tested using actual survey data from the YSTAR-NEOPAT telescope system. For the detected candidates, we performed eyeball inspection of animated images to confirm validity of asteroid detections. Main conclusions include followings. First, the optical distortion in the YSTAR-NEOPAT wide-field images can be properly corrected by comparison with USNO-B1.0 catalog and the astrometric accuracy can be preserved at around 1.5 arcsec. Secondly, image subtraction provides more robust and accurate detection of moving objects. For two different thresholds of 2.0 and $4.0\sigma$, image subtraction method uncovered 34 and 12 candidates and most of them are confirmed to be real. Starlist comparison method detected many more candidates, 60 and 6 for each threshold level, but nearly half of them turned out to be false detections.

• Journal of Life Science
• /
• v.17 no.2 s.82
• /
• pp.279-285
• /
• 2007

Detection of Mycoplasma DNA from the 30 cases of cancer tissues and the normal tissues surrounding the cancer tissues obtained from the patients with gastric cancer and the other 30 cases of cancer tissues and the normal tissues surrounding the cancer tissues obtained from the patients with colon cancer were evaluated by polymerase chain reaction(PCR). The PCR products were sequenced using an ABI 377 automatic DNA sequencer, and these sequences were confirmed by comparing sequences with the database of the National Center for Biotechnology Information BLAST network server. Mycoplasmas DNA were defected in 18 (60%) cases of normal tissues which were around gastric cancer and were 13 (43.3%) cases of gastric cancer tissues. Mycoplasmas DNA were detected in 15(50%) cases of normal tissues which were around colon cancer and 12 (40%) cases of colon cancer tissues. The M. faucium, M. subdolum, M. salivarium, M. auris, M. hyosynoviae, and M. conjunctivae were detected from the gastric cancer tissues. The M. faucium, M. subdolum,, M. salivarium, M. auris, M. hyosynoviae, M. bovigenitalium and M. pulmonis were detected from the normal tissues around gastric cancer. The M. faucium, M. subdolum, M. salivarium, M. auris, M. hyosynoviae, M. synoviae M. bovigenitalium, M. gallinarum, and M. moatsii were detected from the colon cancer. The M. faucium, M. subdolum, M. salivarium, M. auris, M. hyosynoviae, M. bovis, M. opalescens, M. bovigenitalium, M. gallinarum, and M. moatsii were detected from the normal tissues around the colon cancer. These results suggest that Mycoplasmas infection may not correlate with gastric cancer and colon cancer, because of the detection rate of Mycoplasmas DNA were not significantly differences between normal and cancer tissues from the patients.

• Journal of Internet Computing and Services
• /
• v.22 no.4
• /
• pp.83-98
• /
• 2021

The purpose of this study to find the factors influencing the fire alarms using IoT firefighting facility management system data of Seoul Fire & Disaster Headquarters, and to present academic implications for establishing an effective prevention system of fire situation. As the number of high and complex buildings increases and former bulidings are advanced, the fire detection facilities that can quickly respond to emergency situations are also increasing. However, if the accuracy of the fire situation is incorrectly detected and the accuracy is lowered, the inconvenience of the residents increases and the reliability decreases. Therefore, it is necessary to improve accuracy of the system through efficient inspection and the internal environment investigation of buildings. The purpose of this study is to find out that false detection may occur due to building characteristics such as usage or time, and to aim of emphasizing the need for efficient system inspection and controlling the internal environment. As a result, it is found that the size(total area) of the building had the greatest effect on the fire alarms, and the fire alarms increased as private buildings, R-type receivers, and a large number of failure or shutoff days. In addition, factors that influencing fire alarms were different depending on the main usage of the building. In terms of time, it was found to follow people's daily patterns during weekdays(9 am to 6 pm), and each peaked around 10 am and 2 pm. This study was claimed that it is necessary to investigate the building environment that caused the fire alarms, along with the system internal inspection. Also, it propose additional recording of building environment data in real-time for follow-up research and system enhancement.

• Journal of radiological science and technology
• /
• v.30 no.1
• /
• pp.13-23
• /
• 2007

In recent years, mammography system is changed rapidly from conventional screen-film system to digital system for application to screening and diagnosis. Digital mammography system provides several advantages over screen-film mammography system. According to the information provided by the manufacturer, digital mammography system offers radiation dose reduction in comparison with screen-film mammography system, because of digital detector, particularly direct digital detector has higher x-ray absorption efficiency than screen-film combination or imaging plate(IP). We measured average glandular doses(AGD) in screen-film mammography(SFM) system with slow screen-film combination, computed mammography(CM) system, indirect digital mammography(IDM) system and direct digital mammography(DDM) system using brest tissue-equivalent phantom(glandularity 30%, 50% and 70%). The results were shown as follows : AGD values for DDM system were highest than those for other systems. Although automatic exposure control(AEC) mode was selected, the curve of the AGD values against thickness or glandularity increased significantly for the SFM system with the uniform target/filter(Mo/Mo) combination. Therefore, the AGD values for the high energy examinations were highest in the SFM system, and those for the low energy examinations were highest in the DDM system. But the curve of the AGD values against thickness and glandularity increased gently for CM system with the automatic selection of the target/filter combination (from Mo/Mo to Mo/Rh or from Mo/Rh to Rh/Rh), and the AGD values were lowest. Consequently, the parameters in mammography for each exposure besides detection efficiency play an important role in oder to estimate a patient radiation dose.