• Advances in Computational Design
• /
• v.5 no.1
• /
• pp.91-109
• /
• 2020

Over the past few decades, the impact of natural, manmade and natech (natural hazard triggering technological disasters) disasters has been devastating, affecting over 4.4 billion people. In spite of recent technological advances, the increasing frequency and intensity of natural disasters and the escalation of manmade threats is presenting a number of challenges that warrant immediate attention. This paper explores the integration of drones or Unmanned Aerial Vehicles (UAV's) into infrastructure monitoring and post-disaster assessment. Through reviewing some of the recent disasters, effectiveness of utilizing UAV's in different stages of disaster life cycle is demonstrated and needed steps for successful integration of UAV's in infrastructure monitoring, hazard mitigation and post-incident assessment applications are discussed. In addition, some of the challenges associated with implementing UAV's in disaster monitoring, together with research needs to overcome associated knowledge gaps, is presented.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.229-240
• /
• 2019

3D geo-spatial model have been widely used in the field of Civil Engineering, Medical, Computer Graphics, Urban Management and many other. Especially, the demand for high quality 3D spatial information such as precise road map construction has explosively increased, MMS and UAV techniques have been actively used to acquire them more easily and conveniently in surveying and geo-spatial field. However, in order to perform 3D modeling by integrating the two data set from MMS and UAV, its so needed an proper registration method is required to efficiently correct the difference between the raw data acquisition sensor, the point cloud data generation method, and the observation accuracy occurred when the two techniques are applied. In this study, we obtained UAV point colud data in Yeouido area as the study area in order to determine the automatic registration performance between MMS and UAV point cloud data using ICP(Iterative Closet Point) method. MMS observations was then performed in the study area by dividing 4 zones according to the level of overlap ratio and observation noise with based on UAV data. After we manually registered the MMS data to the UAV data, then compared the results which automatic registered using ICP method. In conclusion, the higher the overlap ratio and the lower the noise level, can bring the more accurate results in the automatic registration using ICP method.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.295-296
• /
• 2016

UAV를 이용하여 정사영상과 수치지도제작을 위해서는 촬영계획대로 촬영해야 한다. 그러나 풍속, 풍향 및 시스템의 결함으로 촬영정확도가 저하된다. 저가 UAV의 waypoint기능을 활용한다면 다소 실수를 줄일 수 있다. 본 연구에서는 waypoint기능을 이용하여 비행정확도를 평가하고 모의촬영을 통해 촬영정확도를 확인하고자 한다.

• The Journal of Korea Robotics Society
• /
• v.11 no.4
• /
• pp.262-269
• /
• 2016

Flight of an autonomous unmanned aerial vehicle (UAV) generally consists of four steps; take-off, ascent, descent, and finally landing. Among them, autonomous landing is a challenging task due to high risks and reliability problem. In case the landing site where the UAV is supposed to land is moving or oscillating, the situation becomes more unpredictable and it is far more difficult than landing on a stationary site. For these reasons, the accurate and precise control is required for an autonomous landing system of a UAV on top of a moving vehicle which is rolling or oscillating while moving. In this paper, a vision-only based landing algorithm using dynamic gimbal control is proposed. The conventional camera systems which are applied to the previous studies are fixed as downward facing or forward facing. The main disadvantage of these system is a narrow field of view (FOV). By controlling the gimbal to track the target dynamically, this problem can be ameliorated. Furthermore, the system helps the UAV follow the target faster than using only a fixed camera. With the artificial tag on a landing pad, the relative position and orientation of the UAV are acquired, and those estimated poses are used for gimbal control and UAV control for safe and stable landing on a moving vehicle. The outdoor experimental results show that this vision-based algorithm performs fairly well and can be applied to real situations.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.23-33
• /
• 2020

Recently, high-resolution images can be easily acquired using UAV (Unmanned Aerial Vehicle), so that it is possible to produce small area observation and spatial information at low cost. In particular, research on the generation of cover maps in crop production areas is being actively conducted for monitoring the agricultural environment. As a result of comparing classification performance by applying RF(Random Forest), SVM(Support Vector Machine) and CNN(Convolutional Neural Network), deep learning classification method has many advantages in image classification. In particular, land cover classification using satellite images has the advantage of accuracy and time of classification using satellite image data set and pre-trained parameters. However, UAV images have different characteristics such as satellite images and spatial resolution, which makes it difficult to apply them. In order to solve this problem, we conducted a study on the application of deep learning algorithms that can be used for analyzing agricultural lands where UAV data sets and small-scale composite cover exist in Korea. In this study, we applied DeepLab V3 +, FC-DenseNet (Fully Convolutional DenseNets) and FRRN-B (Full-Resolution Residual Networks), the semantic image classification of the state-of-art algorithm, to UAV data set. As a result, DeepLab V3 + and FC-DenseNet have an overall accuracy of 97% and a Kappa coefficient of 0.92, which is higher than the conventional classification. The applicability of the cover classification using UAV images of small areas is shown.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.1
• /
• pp.1-10
• /
• 2017

An UAV (Unmanned Aerial Vehicle) is a flight system that is designed to conduct missions without a pilot. Compared to traditional airborne-based photogrammetry, UAV-based photogrammetry is inexpensive and can obtain high-spatial resolution data quickly. In this study, we aimed to classify the land cover using high-spatial resolution images obtained using a UAV. An RGB camera was used to obtain high-spatial resolution orthoimage. For accurate classification, multispectral image about same areas were obtained using a multispectral sensor. A DSM (Digital Surface Model) and a modified NDVI (Normalized Difference Vegetation Index) were generated using images obtained using the RGB camera and multispectral sensor. Pixel-based classification was performed for twelve classes by using the RF (Random Forest) method. The classification accuracy was evaluated based on the error matrix, and it was confirmed that the proposed method effectively classified the area compared to supervised classification using only the RGB image.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.1
• /
• pp.179-190
• /
• 2017

A terrestrial LiDAR survey was conducted and unmanned aerial vehicle(UAV) images were taken for target cultural properties to present the utilization measures of terrestrial LiDAR and UAV in three-dimensional modeling of cultural properties for the identification of the status and restoration of cultural properties. Then the accuracy of the point clouds generated through this process was compared, an overlap analysis of the 3D model was conducted, and a convergence model was created. According to the results, the modeling with terrestrial LiDAR is more appropriate for precise survey because 3D modeling for the detection of displacement and deformation of cultural properties requires an accuracy of mm units. And UAV model has limitation as the impossibility of detailed expression of parts with sharp unevenness such as cracks of bricks. However, it is found that the UAV model has a wide range of modeling and has the advantage of modeling of real cultural properties. Finally, the convergence model created in this study using the advantages of the terrestrial LiDAR model and the UAV model could be efficiently utilized for the basic data development of cultural properties.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.2
• /
• pp.3-9
• /
• 2014

With broadcasting telecommunication, rapid change detection, and construction of spatial information, a long reconnaissance, resources detection in dangerous area and natural disasters, which are difficult for manned aerial vehicles to perform, international recognition in UAV merely being used for limited military purposes has been changed and its demand for both civil and military purpose have been increased. However, considering the current situation that availability of UAV varies and its working areas also broaden, the stability of UAV and the problems of privacy protection are more important in integrated operation of UAV. In particular, the application of UAV system is urgent for the area where rapid decision making due to expedite data construction such as disaster, calamity, and the acquisition of spatial information for small area are required. However, since technical stability for UAV system and institutional regulation in regard of spatial information are not examined, and UAV system has not been integrated with aerial photograph, the limitation of UAV system has been presented. Thus, this study is aimed at analyzing domestic and foreign research trend and institutional research trend in terms of integrated UAV operation, and proposing its implications and the availability of integrated UAV operation for future national spatial information data construction.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.871-876
• /
• 2022

In the construction industry, fatal accidents related to scaffolds frequently occur. To prevent such accidents, scaffolds should be carefully monitored for their safety status. However, manual observation of scaffolds is time-consuming and labor-intensive. This paper proposes a method that automatically analyzes the installation status of scaffold joints based on images acquired from a Unmanned Aerial Vehicle (UAV). Using a deep learning-based object detection algorithm (YOLOv5), scaffold joints and joint components are detected. Based on the detection result, a two-stage rule-based classifier is used to analyze the joint installation status. Experimental results show that joints can be classified as safe or unsafe with 98.2 % and 85.7 % F1-scores, respectively. These results indicate that the proposed method can effectively analyze the joint installation status in UAV-acquired scaffold images.

• Journal of Satellite, Information and Communications
• /
• v.12 no.1
• /
• pp.43-48
• /
• 2017

Recently, demands on civilian UAV (Unmanned Aerial Vehicle) has been increasing and appropriate communication system is required for the UAV. In this paper, the performance of the UAV communication system using commercial wireless mobile network is discussed. The main service area of the wireless mobile network is ground level however the flying range of the UAV is normally in high altitude. Because of this mismatch of service area the performance of the UAV communication system is degraded in high altitude. To compensate performance degradation of the UAV communications system in high altitude, adaptive array antenna is introduced which is able to overcome altitude limitation of the UAV communication system.