• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Journal of Aerospace System Engineering
• /
• v.17 no.4
• /
• pp.58-66
• /
• 2023

The latest global issues are the Space economy and low-orbit Space communication. 3GPP announced Release 17 standardization in June 2022, and in this regard, the United States prepared a strategy to enhance the competitiveness of the low-orbit 5G-NTN Space industry, and create an ecosystem at the national level in March 2023. Global smartphone semiconductor manufacturers have announced the development and verification results of standard-based chip technology, and satellite communication operators are launching low-orbit 5G-NTN Space communication services and rate products through convergence between terrestrial communication networks. This study diagnoses the current status of Korea's low-orbit 5G-NTN space communication ecosystem. We present our ecosystem creation strategy in terms of fair competition in the market, the service legal system, and the national R&D governance system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.86-86
• /
• 2023

최근에 들어 환경보전과 지속가능한 하천관리의 중요성이 대두되고 있으며, 통합물관리에 있어 수리량과 수질을 연계한 통합 모니터링의 필요성이 커지고 있다. 수리량과 수질 분야에 대한 모니터링 기술은 지속적인 연구가 이루어져 왔으나, 각 분야의 개별적 연구로 인해 수리량과 수질을 통합하여 모니터링 하는 기술 개발은 미흡한 수준이다. 또한 수질 측정은 수질오염공정시험기준에 있는 채수 기준에 따라 채수하여 측정하고 있으며, 채수 지점은 하천의 수심별로 달리하여 정해진다. 수리 측정은 현장계측을 통한 2차원적 계측으로 진행하고 있어 수질 측정 시 채수지점과 수리 측정지점은 일치하지 않는다. 동일 지점에서의 수질과 수리량을 동시에 고려하고 있지 못한 모니터링은 본류와 지류의 혼합거동이 많은 국내 하천 특성을 반영하지 못한다. 또한 현재의 수질·수리 모니터링은 ADCP나 다항목수질측정기 같은 고가의 장비를 운영하며, 홍수기와 같은 고위험 계측 조건에서 인력을 통해 측정하고 있기에 고비용의 장비운영비와 인명 피해를 야기시키고 있다. 따라서 무인 원격 기술을 적용한 하천 모니터링 기술과 수질과 수리량의 데이터 연계를 통한 3차원 모니터링 기술의 확보는 하천관리에 있어 매우 필수적이다. 본 연구에서는 수중 무인 원격이동체인 ROV와 무인 원격이동체(USV)를 활용한 3차원 수질·수리 모니터링 기술 개발에 관한 연구를 수행하였다. 국내 하천 특성을 고려한 혼합거동을 분석하기 위해 ROV에 수중 GPS 장비와 수질센서를 부착시켜 수중 내 2차원으로 측정되는 수리량과 동일한 좌표를 가지는 수질자료를 계측하여 하천의 연직 분포와 수평적 분포를 통해 화학적 수리적 거동을 분석하여 하천의 3차원 혼합거동 양상을 판단할 수 있었다. 이와 같은 무인 원격이동체를 통한 3차원 수질·수리 모니터링 기술은 하천의 3차원 분석에서 수질·수리량 보간 자료로 활용 가능하며, 효율적인 모니터링을 통하여 하천 전반 및 통합물관리에 있어 크게 기여할 것이라 사료된다.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.9-21
• /
• 2023

The recent conflict between Russia and Ukraine underscores the significant of military logistics support in modern warfare. Military logistics support is intricate and specialized, and traditionally centered on the mission-level operational analysis and functional models. Nevertheless, there is currently increasing demand for military logistics support even at the engagement level, especially for resupply using unmanned transport assets. In response to the demand, this study proposes a task model of the military logistics support for engagement-level analysis that relies on the logic of ammunition resupply below the battalion level. The model employs a decisions tree to establish the priority of resupply based on variables such as the enemy's level of threat and the remaining ammunition of the supported unit. The model's feasibility is demonstrated through a combat simulation using OneSAF.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2927-2934
• /
• 2023

The influence of the atmospheric radon background on the airborne gamma spectrum can seriously affect researchers' judgement of ground radiation information. However, due to load and endurance, unmanned aerial vehicle (UAV)-borne gamma-ray spectrometry is difficulty installing upward-looking detectors to monitor atmospheric radon background. In this paper, an advanced spectral-ratio method was used to correct the atmospheric radon background for a UAV-borne gamma-ray spectrometry in Inner Mongolia, China. By correcting atmospheric radon background, the ratio of the average count rate of U window in the anomalous radon zone (S5) to that in other survey zone decreased from 1.91 to 1.03, and the average uranium content in S5 decreased from 4.65 mg/kg to 3.37 mg/kg. The results show that the advanced spectral-ratio method efficiently eliminated the influence of the atmospheric radon background on the UAV-borne gamma-ray spectrometry to accurately obtain ground radiation information in uranium exploration. It can also be used for uranium tailings monitoring, and environmental radiation background surveys.

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.473-480
• /
• 2023

This study evaluated a novel method of defining the automatic flight path of unmanned aerial vehicles (UAVs) for search and rescue missions in a VR environment. The developed VR content reserves miniature digital twins of a building in the fire and a steep mountain terrain site. The users drow the UAV's scanning path using hand gestures on the surface of digital twins, and then the UAV make an automatic flight along the defined path. According to human-in-the-loop simulation tests comparing the novel method with a conventional manual flight task with 19 participants, the novel method did not improve the mission performance but participants felt a lower mental workload. The designer may need to consider the automation support on the vulnerable points of the SAR mission environment while maintaining experts' mapping capability.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.465-468
• /
• 2022

The incidence of traffic accidents is increasing every year, and Korea is among the top OECD countries. In order to improve this, various road traffic laws are being implemented, and various traffic control methods using equipment such as unmanned speed cameras and traffic control cameras are being applied. However, as drivers avoid crackdowns by detecting the location of traffic control cameras in advance through navigation, a mobile crackdown system that can be cracked down is needed, and research is needed to increase the recognition rate of vehicle license plates on the side of the road for accurate crackdown. This paper proposes a method to improve the vehicle number recognition rate on the road side by applying a gradient correction algorithm using image processing. In addition, custom data learning was conducted using a CNN-based YOLO algorithm to improve character recognition accuracy. It is expected that the algorithm can be used for mobile traffic control cameras without restrictions on the installation location.

• Journal of Information Technology Services
• /
• v.22 no.2
• /
• pp.71-92
• /
• 2023

Globally, under the leadership of advanced ICT countries, the private sector is promoting various policies to promote the digital transformation of public services. Looking at the research trend, design of public service indicators, development of evaluation system, and empirical research are being carried out steadily, but there are insufficient research cases on models in which the private sector participates in the planning, development, and operation of public services. In this study, Private-centric digital public service suitability evaluation indicators were discovered through interviews with experts in various fields, and weights for each indicator were analyzed through AHP evaluation. In addition, by applying the analysis results to 18 digital public services on a trial basis, the importance and priority of evaluation indicators for each service were derived, and at the same time, the evaluation framework was designed and applied to diagnose implications. As a result of the study, 'social utility', 'corporate acceptability', and 'public acceptability' were selected as the top three indicators of suitability evaluation. At this time, it was analyzed that the weight of the 'company acceptability' index, which includes sub-indices such as 'service profitability', 'service scalability', and 'private initiative possibility', was the highest among the three top indicators. As a result of the demonstration for public services, "IoT facility unmanned remote monitoring service", "blockchain real estate transaction service", and "digital twin disaster prediction service" were evaluated as the most suitable public services for the transition to the private sector.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.9
• /
• pp.81-90
• /
• 2016

Recently drones have become popular enough to be one of the hobby. The drone refers to an unmanned aerial vehicle which can fly and be steered by a radio wave without a pilot and it has a airplane or helicopter shape. The drone was first started to be used from military purpose, but its usage has been expanded to the private such as construction site, crop-dusting, field discovery, freight shipping and drones to prevent cheating. However the drone that we can see often in the market is expansive, hard to be repaired when it broken down and has a discomfort of the short flight time. In this paper, to solve an uncomfortable talk on the cheap 8-bits microcontrollers ATmega128 Using drone for implementation. Axes gyroscope and accelerometers mcu between posture an attitude control, communications through drone control, pid. Receiver input them into transmitter signals of movements to control drone c the programming was implemented in on the basis of language. drone using ATmega128 microcontroller is possible hovering, By utilizing a pin that are not required for control it can be used as a drone for a variety of uses.

• Journal of Animal Science and Technology
• /
• v.65 no.3
• /
• pp.638-651
• /
• 2023

The objective of this study was to quantitatively estimate the level of grazing area damage in outdoor free-range pig production using a Unmanned Aerial Vehicles (UAV) with an RGB image sensor. Ten corn field images were captured by a UAV over approximately two weeks, during which gestating sows were allowed to graze freely on the corn field measuring 100 × 50 m². The images were corrected to a bird's-eye view, and then divided into 32 segments and sequentially inputted into the YOLOv4 detector to detect the corn images according to their condition. The 43 raw training images selected randomly out of 320 segmented images were flipped to create 86 images, and then these images were further augmented by rotating them in 5-degree increments to create a total of 6,192 images. The increased 6,192 images are further augmented by applying three random color transformations to each image, resulting in 24,768 datasets. The occupancy rate of corn in the field was estimated efficiently using You Only Look Once (YOLO). As of the first day of observation (day 2), it was evident that almost all the corn had disappeared by the ninth day. When grazing 20 sows in a 50 × 100 m² cornfield (250 m²/sow), it appears that the animals should be rotated to other grazing areas to protect the cover crop after at least five days. In agricultural technology, most of the research using machine and deep learning is related to the detection of fruits and pests, and research on other application fields is needed. In addition, large-scale image data collected by experts in the field are required as training data to apply deep learning. If the data required for deep learning is insufficient, a large number of data augmentation is required.