• Journal of Korea Society of Industrial Information Systems
• /
• 제27권2호
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• Journal of the Korea Institute of Building Construction
• /
• 제22권6호
• /
• pp.681-688
• /
• 2022

In this study, the process of drone photography, automatic volume calculation, total floor area conversion, and waste calculation was constructed as a QGIS plug-in to predict the demolition waste (DW) generated in an aged area where drawing information or building information is uncertain. Through a case study, the high consistency between the automatically calculated volume using the drone and the BIM volume based on the field measurement was confirmed. Field application was carried out for the planned demolition work site, and the consistency between the drone-based volume and the actual measurement-BIM-based volume was reconfirmed. The waste generation unit was applied and the amount of DW was calculated by setting the floor height and building type, and the entire process was completed within 6 hours. Although the difference between building information and building objects through drones occurred according to the setting of temporary structures, loads, and floor heights, it was found that the actual amount of DW was generated more than the initial estimate. It is expected that measures to improve the accuracy of volume and floor area conversion will be required through case studies in the future.

• KIPS Transactions on Software and Data Engineering
• /
• 제12권1호
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• KIPS Transactions on Software and Data Engineering
• /
• 제12권2호
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• Journal of the Society of Disaster Information
• /
• 제18권4호
• /
• pp.883-890
• /
• 2022

Purpose: Currently, in the case of domestic fire fighting facility design, it is difficult to secure highquality manpower due to low design costs and overheated competition between companies, so there is a limit to improving the fire safety performance of buildings. Accordingly, AI-based firefighting design solutions were studied to solve these problems and secure leading fire engineering technologies. Method: Through AutoCAD, which is widely used in existing fire fighting design, the procedures required for basic design and implementation design were processed, and AI technology was utilized through the YOLO v4 object recognition deep learning model. Result: Through the design process for fire fighting facilities, the facility was determined and the drawing design automation was carried out. In addition, by learning images of doors and pillars, artificial intelligence recognized the part and implemented the function of selecting boundary areas and installing piping and fire fighting facilities. Conclusion: Based on artificial intelligence technology, it was confirmed that human and material resources could be reduced when creating basic and implementation design drawings for building fire protection facilities, and technology was secured in artificial intelligence-based fire fighting design through prior technology development.

• Journal of the Korean Association of Geographic Information Studies
• /
• 제26권3호
• /
• pp.85-96
• /
• 2023

This study developed and evaluated a safe route guidance service for electric personal assistive mobility device used mainly by the mobility impaired people to improve their mobility. Thirteen underlying factors affecting the mobility of electric personal assistive mobility device have been derived through a survey with the mobility impaired people and employees in related organizations in Busan Metropolitan City. After assigning safety scores to individual factors and identifying the relevant factors along routes of interest with an object detection AI model, the safe route for electric personal assistive mobility device was provided through an optimal path-finding algorithm. As a result of comparing the general route of T-map and the recommended route of this study for the identical routes, the latter had relatively fewer obstacles and the gentler slope than the former, implicating that the recommended route is safer than the general one. As future works, it is necessary to enhance the function of a route guidance service based on the real-time location of users and to conduct spot investigations to evaluate and verify its social acceptability.

• Journal of the Korea Society for Simulation
• /
• 제32권3호
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• Journal of IKEEE
• /
• 제27권3호
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Journal of the Korea Society for Simulation
• /
• 제19권1호
• /
• pp.63-71
• /
• 2010

In modern war, Intercept Performance of SAM(Surface to Air Missile) is gaining importance as range and precision of Missile and Guided Weapon on information warfare have been improved. An aerial defence system using Surface-to-air Radar and Guided Missile is needed to be built for prediction and defense from threatening aerial attack. When developing SAM, M&S is used to free from a time limit and a space restriction. M&S is widely applied to education, training, and design of newest Weapon System. This study was conducted to develop simulator for evaluation of Intercept Performance of SAM. In this study, architecture of Intercept Performance of SAM analysis simulator for estimation of Intercept Performance of various SAM was suggested and developed. The developed Intercept Performance of SAM analysis simulator was developed by C++ and Direct3D, and through 3D visualization using the Direct3D, it shows procedures of the simulation on a user animation window. Information about design and operation of Fighting model is entered through input window of the simulator, and simulation engine consisted of Object Manager, Operation Manager, and Integrated Manager conducts modeling and simulation automatically using the information, so the simulator gives user feedback in a short time.

• Journal of Industrial Convergence
• /
• 제20권12호
• /
• pp.195-202
• /
• 2022

Underground Geospatial Information Map Management System(UGIMMS) integrates various underground facilities in the underground space into 3D mesh data, and supports to check the 3D image and location of the underground facilities in the mobile app. However, there is a problem that it takes a long time to run in the app because various underground facilities can exist in some areas executed by the app and can be seen layer by layer. In this paper, we propose a deep learning-based K-means vertex clustering algorithm as a method to reduce the execution time in the app by reducing the size of the data by reducing the number of vertices in the 3D mesh data within the range that does not cause a problem in visibility. First, our proposed method obtains refined vertex feature information through a deep learning encoder-decoder based model. And second, the method was simplified by grouping similar vertices through K-means vertex clustering using feature information. As a result of the experiment, when the vertices of various underground facilities were reduced by 30% with the proposed method, the 3D image model was slightly deformed, but there was no missing part, so there was no problem in checking it in the app.