• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.151-162
• /
• 2022

Recently, the forests in Korea have accumulated damage due to continuous forest disasters, and the need for technologies to monitor forest managements is being issued. The size of the affected area is large terrain, technologies using drones, artificial intelligence, and big data are being studied. In this study, a standard dataset were conducted to develop an algorithm that automatically detects suspicious trees damaged by forest pests using deep learning and drones. Experiments using the YOLO model among object detection algorithm models, the YOLOv4-P7 model showed the highest recall rate of 69.69% and precision of 69.15%. It was confirmed that YOLOv4-P7 should be used as an automatic detection algorithm model for trees suspected of being damaged by forest pests, considering the detection target is an ortho-image with a large image size.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.814-836
• /
• 2021

Wildlife ecologists and biologists recapture deer to collect tracking data from deer collars or wait for a drop-off of a deer collar construction that is automatically detached and disconnected. The research teams need to manage a base camp with medical trailers, helicopters, and airplanes to capture deer or wait for several months until the deer collar drops off of the deer's neck. We propose an intelligent robust base-station research with a low-cost and time saving method to obtain recording sensor data from their collars to a listener node, and readings are obtained without opening the weatherproof deer collar. We successfully designed the and implemented a robust base station system for automatically collecting data of the collars and listener motes in harsh wilderness environments. Intelligent solutions were also analyzed for improved data collections and pattern predictions with drone-based detection and tracking algorithms.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.501-511
• /
• 2022

Three-dimensional (3D) models have become crucial for improving civil infrastructure analysis, and they can be used for various purposes such as damage detection, risk estimation, resolving potential safety issues, alarm detection, and structural health monitoring. 3D point cloud data is used not only to make visual models but also to analyze the states of structures and to monitor them using semantic data. This study proposes automating the generation of high-quality 3D point cloud data and removing noise using deep learning algorithms. In this study, large-format aerial images of civilian infrastructure, such as cut slopes and dams, which were captured by drones, were used to develop a workflow for automatically generating a 3D point cloud model. Through image cropping, downscaling/upscaling, semantic segmentation, generation of segmentation masks, and implementation of region extraction algorithms, the generation of the point cloud was automated. Compared with the method wherein the point cloud model is generated from raw images, our method could effectively improve the quality of the model, remove noise, and reduce the processing time. The results showed that the size of the 3D point cloud model created using the proposed method was significantly reduced; the number of points was reduced by 20-50%, and distant points were recognized as noise. This method can be applied to the automatic generation of high-quality 3D point cloud models of civil infrastructures using aerial imagery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.779-800
• /
• 2024

Unmanned Aerial Vehicle (UAV) networks, also known as drone networks, have gained significant attention for their potential in various applications, including communication. UAV networks for communication involve using a fleet of drones to establish wireless connectivity and provide communication services in areas where traditional infrastructure is lacking or disrupted. UAV communication networks need to be highly secured to ensure the technology's security and the users' safety. The proposed survey provides a comprehensive overview of the current state-of-the-art UAV network security solutions. In this paper, we analyze the existing literature on UAV security and identify the various types of attacks and the underlying vulnerabilities they exploit. Detailed mitigation techniques and countermeasures for the protection of UAVs are described in this paper. The survey focuses on the implementation of novel technologies like Q-learning, blockchain, IRS, and mmWave. This paper discusses network simulation tools that range in complexity, features, and programming capabilities. Finally, future research directions and challenges are highlighted.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.97-104
• /
• 2018

In the conventional direction finding, the antenna is installed at a high position on the ground to detect the position of the target with the environment of the LOS(Line of Sight) as much as the signal receiving environment. However, in order to configure such environment, high cost and installation time were required. In this paper, we use TDOA(Time Difference of Arrival) technique to utilize drones in direction finding, so that four drones can be used for directions finding simulation. Simulations based on drone and TDOA direction finding were constructed using additional signal processing Taylor series and Exact Interactive Algorithm. In the simulation, the receiving power is defined by using the 800MHz path-loss model using the GPS information of the ground direction detection, and the position estimation performance is analyzed when the TDOA technique, the Taylor series, and the Exact Interactive Alogrithm are applied.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.73-82
• /
• 2023

Marine debris not only affects the survival of marine life, water pollution, and scenery but also has secondary effects on economic loss and human health. While research on underwater and surface debris is actively ongoing, solutions to marine debris in hard-to-reach blind spots are being developed slowly. To address this problem, we utilize drones to detect and track marine debris in blind spots such as tetrapods. The detected debris is then visualized by calculating its location coordinates using the drone's GPS, altitude, and heading values. The proposed method of using drones for detecting marine debris and matching it with longitude and latitude coordinates provides an effective solution to the problem of marine debris in blind spots.

• Journal of Korean Society of Disaster and Security
• /
• v.16 no.4
• /
• pp.129-136
• /
• 2023

A special offshore bridge with a high pylon has special structural features.Special offshore bridges have inspection blind spots that are difficult to visually inspect. To solve this problem, safety inspection methods using drones are being studied. In this study, image data of the pylon of a special offshore bridge was acquired using a drone. In addition, an artificial intelligence algorithm was developed to detect damage to the pylon surface. The AI algorithm utilized a deep learning network with different structures. The algorithm applied the stacking ensemble learning method to build a model that formed the ensemble and collect the results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1003-1004
• /
• 2017

본 연구에서는 실내 환경에서 드론의 측위를 위한 마커 인식 및 검출 기술을 소개한다. 기존 실내 측위를 위한 기술인 Global Positioning System이나 Wi-Fi를 이용한 삼각측량 기법은 실내 환경에서 각각의 성질로 인하여 사용하기 어려운 점이 있다. 본 논문에서는 2차원 바코드와 마커 등의 객체를 드론의 카메라를 이용한 실시간 영상 전송을 통하여 검출하여 위치 정보를 획득하는 기술을 소개한다. 실험에서는 드론의 카메라를 통하여 실시간 전송된 영상에서 OpenCV V2.4.10을 통하여 객체를 검출하였고, 카메라와 객체 사이의 거리와 바코드 크기에 따른 2차원 바코드의 검출 여부를 보였으며 15*15cm의 2차원 바코드는 비교적 잘 인식하였으나 비교적 작은 11*11cm의 2차원 바코드는 거리가 멀어질 수록 인식이 힘들어지는 결과를 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.965-968
• /
• 2017

드론이라고도 불리는 소형 무인기는 비전 시스템을 대부분 갖추고 있어 비전을 응용한 기술이 적합한 플랫폼이며 특히 랜드 마크 기반 위치 추적 방법은 드론과 지상 로봇과 같은 다른 플랫폼 간의 협업을 위한 효율적인 방법 중 하나이다. 본 논문에서는 드론과 지상 로봇의 협업 시스템을 위하여 기준 마커를 검출하는 연구에 대하여 서술한다. 기준 마커 중 하나인 ArUco는 바코드보다 간단한 내부 코드를 가지고 있다. 기준 마커의 카메라 캘리브레이션을 통하여 카메라와 마커의 자세 추정이 가능하다. 성능 평가 실험을 통하여 형태가 간단한 마커, AprilTags, ArUco 간 성능 비교를 하였고 92%의 정확도를 얻어내었으며 ArUco의 적합한 이진화 알고리즘을 제시하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.335-337
• /
• 2021

최근 드론의 용도는 취미, 공연, 농업, 안전, 군사, 연구, 물자수송 등 다양한 분야와 목적으로 활용되고 있다. 더불어 드론의 불법적 활용으로 인한 안전 및 법적 문제 또한 빈번히 발생하고 있어, 이런 문제들을 예방하기 위한 드론의 탐지 기술이 활발히 연구되고 있다. 본 논문은 카메라로 촬영된 영상에서 조류와 같은 다른 객체와 구별하여 드론을 탐지하는 기술과 상공에서 바라본 객체들을 탐지하는 기술을 구현한다. 제안 방법은 딥러닝 기반의 YOLOv4를 사용하였다. UAV_123 데이터세트로 학습한 실험 결과, mAP는 85%, Recall은 85%, Precision은 81%의 정확도를 보였다. 제안 방법은 인명 구조, 배송, 건축 뿐만 아니라 안티 드론 시장에서도 효과적으로 활용될 수 있을 것으로 기대된다.