• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.33-40
• /
• 2022

In this paper, we propose a system that analyzes drone photographic images of panel-type factory roofs and conducts abnormal detection of bolts. Currently, inspectors directly climb onto the roof to carry out the inspection. However, safety accidents caused by working conditions at high places are continuously occurring, and new alternatives are needed. In response, the results of drone photography, which has recently emerged as an alternative to the dangerous environment inspection plan, will be easily inspected by finding the location of abnormal bolts using deep learning. The system proposed in this study proceeds with scanning the captured drone image using a sample image for the situation where the bolt cap is released. Furthermore, the scanned position is discriminated by using AI, and the presence/absence of the bolt abnormality is accurately discriminated. The AI used in this study showed 99% accuracy in test results based on VGGNet.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.233-240
• /
• 2024

In this study, we introduce a system for real-time monitoring of field conditions within an industrial complex using a 5G network UAV (: Unmanned Aerial Vehicle). When a monitoring event occurs in a sensor mounted on a UAV (detection of fire, harmful gas, or industrial disaster type human accident), key information from the sensor is transmitted to the UAS (: Unmanned Aerial System) application server. As a result of this information transmission and processing, managers or operators of the Industrial Complex Corporation were able to secure legal basis data for fatal accidents, fires, and detection of harmful gases at sites within the Industrial Complex Corporation through trigger processing for each accident risk situation.

• Journal of the Korean GEO-environmental Society
• /
• v.21 no.6
• /
• pp.13-17
• /
• 2020

In the era of the fourth industrial revolution, drones are being used in various civil engineering fields. Currently, the construction and maintenance of slopes are generally managed by manpower. This method has a risk of safety accidents, and it is difficult to accurately evaluate the slope because it is difficult to secure the vision. In this paper, the effects of RTK and GCP on the 3D model of the slope were studied by using digital images taken by the drone. GNSS coordinates were measured for nine points to compare the quality of the slope 3D model, three points of which were used as the check points and the remaining points were used as GCPs. When making the 3D model of the slope using high-accuracy geotagging images using RTK, it was found that the error at the check point decreases as the number of GCP increases. Even if GNSS was used, it was found that the error at the check points of the 3D slope model was not significant when the GCPs were applied. However, it was found that even if high-accuracy geotagging images are used using the RTK module, a significant error occur when the 3D slope model is created without applying GCPs. Therefore, it can be stated that GCP must be applied to create the 3D slope model in which information about the height as well as plane information is important.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.11a
• /
• pp.1271-1276
• /
• 2017

산업이 고도화되고 기술발전이 가속화되고 있지만, 생산현장에서의 사고와 재해는 아직까지도 지속적으로 발생하고 있다. 이는 시스템의 대규모화, 복잡화, 다양화 등에 따라 나타나는 불안전한 상태(unsafe condition)와 근로자의 안전불감증, 낮은 학습효과, 안전문화 비활성화 등을 포함하는 불안전한 행동(unsafe behavior)에 기인한다. 최근 4차 산업혁명이 대두되면서, 인간과 기계 시스템 사이의 상호작용이 활발해지고, 데이터 가용성과 알고리즘 우수성이 확보되면서, 산업현장에서도 시스템과 공정안전을 위해 최신 기술을 활용하려는 시도가 시작되고 있다. 궁극적으로는, 품질 관리, 고장분석, 작업환경관리, 보건관리 등 생산관리의 다양한 범위에 새로운 산업안전혁신을 가져올 것으로 기대된다. 본 논문에서는 사물인터넷, 드론, 인공지능 등 4차 산업혁명 시대의 하드웨어와 소프트웨어의 결합의 사례를 통해 안전한 생산현장은 물론 신뢰성할 수 있는 공공 및 사회를 위한 지능형 시스템 구축의 필요성을 제시하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1105-1106
• /
• 2019

고도성장 당시 건축되었던 사회기반시설들은 노후화로 인한 안전사고의 위험성이 부각되고 있다. 사회기반시설 중 교량의 경우 건축방식, 기후에 따른 안전점검 간 제약사항이 생긴다. 본 논문에서는 드론을 통해 점검이 필요한 교량을 촬영한다. 교량의 촬영 데이터를 정합 이미지로 생성하여 교량 내 유지보수를 위한 교량 모니터링 시스템을 제안한다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.7
• /
• pp.622-628
• /
• 2016

The prosperity of IT technologies and the removal of restrictions regarding Unmanned Aerial Vehicles (UAVs), also known as drones, have driven growth in their popularity. However, without a proper solution to the problem of accident avoidance for UAVs, this popularity increases the potential for collisions between UAVs and between UAV and terrain features. These collisions can occur because UAVs to date have flown using radio control or image recognition based autonomous navigation. Therefore, we propose efficient UAV routing schemes to tackle the collision problem using vehicular communication systems. Performance evaluation by computer simulation shows that the proposed methods effectively reduce the collision probability and improve the routing efficiency of the UAV. Furthermore, the proposed algorithms are compatible and can be directly applied with small overhead to the commercial vehicular communication system implementation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.530-538
• /
• 2020

Safety inspections of outdoor advertisements are conducted to determine the aging status, specifications, and compliance with design documents. Regular inspections are conducted on outdoor advertisements from a safety perspective, as they not only undermine the aesthetic elements of the city but also could cause falls on roads or pedestrian paths. However, the current safety inspection methods are at risk of various accidents during the inspection advertisements on the outer wall of the building. And it is difficult to conduct in-depth inspections on them if they are fixed to the elevation of the building. Furthermore, there also is a risk of safety accidents, such as advertising structures falling onto a pedestrian path. Therefore, this paper aims to enhance the safety inspection system of outdoor advertisements using drones. This paper also intends to propose measures for facility inspection history management such as safety inspection cycle, maintenance, and removal of signboards.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.925-932
• /
• 2018

This study deals with Turbo-Roundabout of Special-Roundabouts. Recently, many rotary intersections are being constructed in Korea, but the effect of the rotary intersection depends on the total entrance traffic volume and the area of the paper. The purpose of this study is to analyze the operation and accident reduction effect of turning traffic signal intersection with small traffic volume into turbo - type turning intersection. The main results are as follows. First, when the traffic volume of the main road is high, the traffic volume of the subway is less than 10 ~ 15%, or when the left turn ratio is less than 30%, it is improved when switching to the turbo type turn intersection instead of the first turn type and second turn type turn intersection Was analyzed. Second, it is considered that turbo type rotary intersection is more effective than first - type rotary intersection, and it is more effective in increasing road capacity because the area of paper is smaller than that of second - order rotary intersection. Third, the number of traffic accidents decreased by 45.9% and the number of injured persons decreased by 76.5% after the conversion of the turnover type turnover to turbo type. 100%), the number of car accidents was 0.3, and the number of casualties was 0 (100%). Finally, the positive evaluation of the user satisfaction survey showed that the improvement in safety, accessibility, and convenience was improved by 60.4%, which was improved by 16.4% to 76.8% after the conversion to the turbo type turnover.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1837-1846
• /
• 2022

The annual increase in chemical accidents is causing damage to life and the environment due to the spread and residual of substances. Environmental damage investigation is more difficult to determine the geographical scope and timing than human damage investigation. Considering the reality that there is a lack of professional investigation personnel, it is urgent to develop an efficient quantitative evaluation method. In order to improve this situation, this paper conducted a chemical accidents investigation using unmanned aerial vehicles(UAV) equipped with various sensors. The damaged area was calculated by Ortho-image and strength of agreement was calculated using the normalized difference vegetation index image. As a result, the Cohen's Kappa coefficient was 0.649 (threshold 0.7). However, there is a limitation in that analysis has been performed based on the pixel of the normalized difference vegetation index. Therefore, there is a need for a chemical accident investigation plan that overcomes the limitations.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1749-1760
• /
• 2022

In modern society, human and social damages caused by natural disasters and frequent disaster accidents have been increased year by year. Prompt access to dangerous disaster sites that are inaccessible or inaccessible using state-of-the-art Earth observation equipment such as satellites, drones, and survey robots, and timely collection and analysis of meaningful disaster information. It can play an important role in protecting people's property and life throughout the entire disaster management cycle, such as responding to disaster sites and establishing mid-to long-term recovery plans. This special issue introduces the National Disaster Management Research Institute (NDMI)'s disaster management technology that utilizes various Earth observation platforms, such as mobile survey vehicles equipped with close-range disaster site survey sensors, drones, and survey robots, as well as satellite technology, which is a tool of remote earth observation. Major research achievements include detection of damage from water disasters using Google Earth Engine, mid- and long-term time series observation, detection of reservoir water bodies using Sentinel-1 Synthetic Aperture Radar (SAR) images and artificial intelligence, analysis of resident movement patterns in case of forest fire disasters, and data analysis of disaster safety research. Efficient integrated management and utilization plan research results are summarized. In addition, research results on scientific investigation activities on the causes of disasters using drones and survey robots during the investigation of inaccessible and dangerous disaster sites were described.