• Korean Journal of Remote Sensing
• /
• v.39 no.1
• /
• pp.87-97
• /
• 2023

Unmanned aerial vehicles (UAVs) can capture high-resolution imagery from a variety of viewing angles and altitudes; they are generally limited to collecting images of small scenes from larger regions. To improve the utility of UAV-appropriated datasetsfor use with deep learning applications, multiple datasets created from variousregions under different conditions are needed. To demonstrate a powerful new method for integrating heterogeneous UAV datasets, this paper applies a combined segmentation network (CSN) to share UAVid and semantic drone dataset encoding blocks to learn their general features, whereas its decoding blocks are trained separately on each dataset. Experimental results show that our CSN improves the accuracy of specific classes (e.g., cars), which currently comprise a low ratio in both datasets. From this result, it is expected that the range of UAV dataset utilization will increase.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.32-39
• /
• 2023

This paper provides a comprehensive overview of UAV classification, tracking, and detection, offering researchers a clear understanding of these fundamental concepts. It elucidates how classification categorizes UAVs based on attributes, how tracking monitors real-time positions, and how detection identifies UAV presence. The interconnectedness of these aspects is highlighted, with detection enhancing tracking and classification aiding in anomaly identification. Moreover, the paper emphasizes the relevance of simulations in the context of drones and UAVs, underscoring their pivotal role in training, testing, and research. By succinctly presenting these core concepts and their practical implications, the paper equips researchers with a solid foundation to comprehend and explore the complexities of UAV operations and the role of simulations in advancing this dynamic field.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.369-370
• /
• 2023

Although the construction industry has become highly advanced, traditional accidents still occur on construction sites, prompting numerous studies and systems aimed at accident prevention using smart construction technology. This study is an exploratory investigation of utilizing unmanned aerial vehicles (UAVs) for safety management. The study aims to verify harmful and hazardous factors that UAVs can detect on construction sites, classify management factors, and define improvement measures to present a checklist for each process. Through this, we hope that smart construction technology will be further expanded and applied for on-site safety management.

• Smart Media Journal
• /
• v.7 no.3
• /
• pp.64-71
• /
• 2018

Utilization of unmanned aerial vehicles (UAVs) are rapidly expanding to various fields ranging from defense, industry, entertainment and personal hobbies. Due to the increased activities of unmanned airplanes, many security problems have emerged, including flight path errors to undesired destinations, secondary threats due to exposed securities caused by the capture of unmanned airplanes in hostile countries. In this paper, we find security vulnerabilities in UAVs such as GPS spoofing, hacking captured video information, malfunction due to signal attenuation through jamming, and exposure of personal information due to image shooting. In order to solve this problem, the stability of the unstructured data is secured by setting the encryption of the video shooting information section using the virtual private network (VPN) to prevent the GPS spoofing attack. In addition, data integrity was ensured by applying personal information encryption and masking techniques to minimize the secondary damage caused by exposure of the UAV and to secure safety. It is expected that it will contribute to the safe use and stimulation of industry in the application field of UAV currently growing.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.61-70
• /
• 2020

The unmanned aerial vehicle that emerged with the 4th Industrial Revolution attracts attention not only from Korea but also from around the world, and its utilization and market size are gradually expanding. For the first time, it was used for military purposes, but it is currently used for transportation, investigation, surveillance, and agriculture. China, along with the US and Europe, is emerging as a leader in the commercial unmanned aerial vehicle market, and Korea, which has the world's seventh-largest technology in related fields, is striving to promote various technology development policies and system improvement related to unmanned aerial vehicles. Military drones will revolutionize the means of war by using a means of war called an unmanned system based on theories such as network-oriented warfare and effect-oriented warfare. Mobile equipment, including drones, is greatly affected by environmental factors such as terrain and weather, as well as technological developments and interests in the field. Now, drones are being used actively in many fields, and especially in the military field, the use of advanced drones is expected to create a new defense environment and provide a new paradigm for war.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.3
• /
• pp.343-350
• /
• 2021

Unmanned aerial vehicles(UAV) photogrammetry provides a cost-effective option for collecting high-resolution 3D point clouds compared with UAV LiDAR and aerial photogrammetry. The main objectives of this study were to (1) validate the accuracy of 3D site model generated, and (2) determine the differences between Digital Elevation Model(DEM) and Digital Surface Model(DSM). In this study, DEM and DSM were shown to have varying degree of accuracy from observed data. The results indicated that the model predictions were considered tend to over- and under-estimated. The range of RMSE of DSM predicted was from 8.2 and 21.3 when compared with the observation. In addition, RMSE values were ranged from 10.2 and 25.8 to compare between DEM predicted and field data. The predict values resulting from the DSM were in agreement with the observed data compared to DEM calculation. In other words, it was determined that the DSM was a better suitable model than DEM. There is potential for enabling automated topography evaluation of the prior-harvest areas by using UAV technology.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.

• Electronics and Telecommunications Trends
• /
• v.32 no.5
• /
• pp.117-126
• /
• 2017

With the advances of high-performance, lightweight hardware components and control software, unmanned aerial vehicles (UAVs) have expanded in terms of use, not only for military applications but also for civilian applications. To complete their task at a remote location, UAVs are generally equipped with a camera, and various sensors and types of hardware devices can be attached according to the particular task. When UAVs capture video images and transmit them into the user's interface, augmented reality (AR) and virtual reality (VR) technologies as a user interface may have advantages in controlling the UAV. In this paper, we review AR and VR applications for UAVs and discuss their future directions.

• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.1
• /
• pp.16-23
• /
• 2011

In this paper, nonlinear model predictive control (NMPC) is addressed to develop formation guidance for multiple unmanned aerial vehicles. An NMPC algorithm predicts the behavior of a system over a receding time horizon, and the NMPC generates the optimal control commands for the horizon. The first input command is, then, applied to the system and this procedure repeats at each time step. The input constraint and state constraint for formation flight and inter-collision avoidance are considered in the proposed NMPC framework. The performance of NMPC for formation guidance critically degrades when there exists a communication failure. In order to address this problem, the modified optimal guidance law using only line-of-sight, relative distance, and own motion information is presented. If this information can be measured or estimated, the proposed formation guidance is sustainable with the communication failure. The performance of this approach is validated by numerical simulations.

• Journal of Engineering Education Research
• /
• v.17 no.5
• /
• pp.17-22
• /
• 2014

Unmanned aerial vehicles (UAVs) that have been recently commercialized can largely be divided into fixed-wing aircraft and rotor aircraft by their styles and flight characteristics. Although the fixed-wing aircraft represents higher power efficiency, higher speed, longer flight distance and larger loading weight than the rotor aircraft, they have a disadvantage of requiring a space for take-off and landing. On the other hand, the rotor aircraft can implement vertical take-off and landing (VTOL) and represents various flight modes (hovering, steep bank turns and low-speed flights). But they require both precision take-off control and attitude control. In this study, we used a quad-tilt rotor UAV to combine advantages in both the fixed-wing aircraft and the rotor aircraft. The quad-tilt rotor (QTR) system was designed and constructed by adding a tilt device with a servo motor to a general quad-rotor vehicle.