• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.871-884
• /
• 2021

The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

• Journal of the Korean Geosynthetics Society
• /
• v.19 no.4
• /
• pp.41-50
• /
• 2020

Since cracks in concrete structures expedite corrosion of reinforced concrete over a long period of time, regular on-site inspections are essential to ensure structural usability and prevent degradation. Most of the safety inspections of facilities rely on visual inspection with naked eye, so cost and time consuming are severe, and the reliability of results differs depending on the inspector. In this study, a portable measuring device that can be used for safety diagnosis and maintenance was developed as a device that measures the width and length of concrete cracks through image analysis of cracks photographed with a camera. This device captures the cracks found within a close distance (3 m), and accurately calculates the unit pixel size by laser distance measurement, and automatically calculates the crack length and width with the image processing algorithm developed in this study. In measurement results using the crack image applied to the experiment, the measurement of the length of a 0.3 mm crack within a distance of 3 m was possible with a range of about 10% error. The crack width showed a tendency to be overestimated by detecting surrounding pixels due to vibration and blurring effect during the binarization process, but it could be effectively corrected by applying the crack width reduction function.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1195-1204
• /
• 2021

Recently, local torrential rain have become more frequent and severe due to abnormal climate conditions, causing a surge in human and properties damage including infrastructures along the river. In this study, water surface elevation prediction algorithm was developed using the LSTM (Long Short-term Memory) technique specialized for time series data among Machine Learning to estimate and prevent flooding of the facilities. The study area is Jamsu Bridge, the study period is 6 years (2015~2020) of June, July and August and the water surface elevation of the Jamsu Bridge after 3 hours was predicted. Input data set is composed of the water surface elevation of Jamsu Bridge (EL.m), the amount of discharge from Paldang Dam (m³/s), the tide level of Ganghwa Bridge (cm) and the number of tweets in Seoul. Complementary data were constructed by using not only structured data mainly used in precedent research but also unstructured data constructed through wordcloud, and the role of unstructured data was presented through comparison and analysis of whether or not unstructured data was used. When predicting the water surface elevation of the Jamsu Bridge, the accuracy of prediction was improved and realized that complementary data could be conservative alerts to reduce casualties. In this study, it was concluded that the use of complementary data was relatively effective in providing the user's safety and convenience of riverside infrastructure. In the future, more accurate water surface elevation prediction would be expected through the addition of types of unstructured data or detailed pre-processing of input data.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.85-92
• /
• 2023

Respiratory infections such as COVID-19 mainly occur within enclosed spaces. The presence or absence of abnormal symptoms of respiratory infectious diseases is judged through initial symptoms such as fever, cough, sneezing and difficulty breathing, and constant monitoring of these early symptoms is required. In this paper, image matching correction was performed for the RGB camera module and the thermal imaging camera module, and the temperature of the thermal imaging camera module for the measurement environment was calibrated using a blackbody. To detection the target recommended by the standard, a deep learning-based object recognition algorithm and the inner canthus recognition model were developed, and the model accuracy was derived by applying a dataset of 100 experimenters. Also, the error according to the measured distance was corrected through the object distance measurement using the Lidar module and the linear regression correction module. To measure the performance of the proposed model, an experimental environment consisting of a motor stage, an infrared thermography temperature screening system and a blackbody was established, and the error accuracy within 0.28℃ was shown as a result of temperature measurement according to a variable distance between 1m and 3.5 m.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.922-929
• /
• 2022

Purpose: The purpose of this paper is to develop a deep learning model to detect fire extinguishers in images taken from CCTVs in underground utility tunnels. Method: Various fire extinguisher images were collected for detection of fire extinguishers in the running-based underground utility tunnel, and a model applying the One-stage Detector method was developed based on the CNN algorithm. Result: The detection rate of fire extinguishers photographed within 10m through CCTV video in the underground common area is over 96%, showing excellent detection rate. However, it was confirmed that the fire extinguisher object detection rate drops sharply at a distance of 10m or more, in a state where it is difficult to see with the naked eye. Conclusion: This paper develops a model for detecting fire extinguisher objects in underground common areas, and the model shows high performance, and it is judged that it can be used for underground common area digital twin model synchronizing.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.111-119
• /
• 2019

The existing smart grid device authentication system is concentrated on DCU, meter reading FEP and MDMS, and the authentication system for smart meters is not established. Although some cryptographic chips have been developed at present, it is difficult to complete the PKI authentication scheme because it is at the low level of simple encryption. Unlike existing power grids, smart grids are based on open two-way communication, increasing the risk of accidents as information security vulnerabilities increase. However, PKI is difficult to apply to smart meters, and there is a possibility of accidents such as system shutdown by sending manipulated packets and sending false information to the operating system. Issuing an existing PKI certificate to smart meters with high hardware constraints makes authentication and certificate renewal difficult, so an ultra-lightweight password authentication protocol that can operate even on the poor performance of smart meters (such as non-IP networks, processors, memory, and storage space) was designed and implemented. As a result of the experiment, lightweight cryptographic authentication protocol was able to be executed quickly in the Cortex-M3 environment, and it is expected that it will help to prepare a more secure authentication system in the smart grid industry.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.318-327
• /
• 2009

In this paper, we propose a 3-D geometric localization method for near-field broadband source in shallow water environments. According to the waveguide invariant theory, slope of the interference pattern which is seen in a sensor spectrogram directly proportional to a range of the source. The relative ratio of the range between source and sensors was estimated by matching of two interference patterns in spectrogram. Then this ratio is applied to the Apollonius's circle which shows the locus of a source whose range ratio from two sensors is constant. Two Apollonius's circles from three sensors make the intersection point that means the horizontal range and the azimuth angle of the source. And this intersection point is constant with source depth. Therefore the source depth can be estimated using 3-D hyperboloid equation whose range difference from two sensors is constant. To evaluate a performance of the proposed localization algorithm, simulation is performed using acoustic propagation program and analysis of localization error is demonstrated. From simulation results, error estimate for range and depth is described within 50 m and 15 m respectively.