• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.1
• /
• pp.37-43
• /
• 2022

Drones, one of the 4th industrial technologies that are expanding from military use to industrial use, are being actively used in the search missions of the National Police Agency and finding missing persons, thereby reducing interest in a wide area and the input of large-scale search personnel. However, legal review of police drone operation is continuously required, and the importance of advanced system for related operations and analysis of captured images in connection with search techniques is increasing at the same time. In this study, in order to facilitate recording, preservation, and monitoring in the concept of precise search and monitoring, it is possible to achieve high efficiency and secure golden time when precise search is performed by constructing spatial information based on photo rather than image data-based search. Therefore, we intend to propose a spatial information construction technique that reduces the resulting data volume by adjusting the unnecessary spatial information completion rate according to the size of the subject. Through this, the scope of use of drone search missions for large-scale areas is advanced and it is intended to be used as basic data for building a drone operation manual for police searches.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.312-314
• /
• 2021

The government sees drones as a key future growth engine, prepares plans to foster the nation-led drone industry, conducts pilot projects in various fields, such as transporting goods, forest protection, monitoring, facility safety diagnosis, and is actively in the use of drones. In particular, the police are attempting to use drones to search for missing people. However, existing drones have a short operating time due to the limitation of battery time. The effectiveness of the existing drones is insufficient because it has no choice but to search by aerial photography on the mountain tops in hillside or dense forest. In this study, we propose an FPV drone that utilizes virtual reality as a drone that can overcome the limitations of searching for missing people.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.179-184
• /
• 2021

Along with the development of the fourth industry, the public sector has increasingly paid more attention to search using drones and real-time monitoring, for various goals. The drones are used and researched to complete a variety of searching and monitoring missions, including search for missing persons, security, coastal patrol and monitoring, speed enforcement, highway and urban traffic monitoring, fire and wildfire monitoring, monitoring of illegal fishing in reservoirs and protest rally monitoring. Police stations, fire departments and military authorities, however, concentrate on the hardware part, so there are little research on efficient communication systems for the real-time monitoring of data collected from high-performance resolution and infrared thermal imagining cameras, and analysis programs suitable for special missions. In order to increase the efficiency of drones with the searching mission, this paper, therefore, attempts to propose an image analysis technique to increase the precision of search by producing image data suitable for searching missions, based on images obtained from drones and provide the foundation for improving relevant policies and establishing proper platforms, based on actual field cases and experiments.

• Korean Security Journal
• /
• no.62
• /
• pp.65-86
• /
• 2020

Drones, which were originally developed for military purpose, have expanded rapidly not only in hobbies, leisure, but also in broadcasting, filming, and public sectors, and search and rescue drones have been used to find four Korean teachers who went to Nepal for volunteer work but went missing in the avalanche. The government is encouraging the use of drones in the public sector as a policy to foster the drone industry, and the market is expected to expand in the future. This study presents improvement measures and specific directions for use of drones by public agencies at a time when the use of drones is expanding in the public sector. To that end, this research reviewed the interviews of relevant experts, analysis of drone operation regulations by public agencies, and the cases of operation of drones for searching missing persons by police. First of all, it will have to secure skilled personnel before the introduction of the drones and then determine the specifications of the drones through sufficient review, and then be put into the mission after careful examination of the drones. Next, it is necessary to draw up a base rule for drone operation and draw up a manual accordingly. Finally, drone flight has the risk of a crash, and it is essential to secure dedicated personnel for drone operation, especially since drones in the public sector are specialized in large scale compared to hobby drones to achieve their purpose. This research only conducted a detailed analysis of the National Police Agency's drones for searching for missing persons, and there are limitations to the number of people interviewed. Subsequent studies will require analysis of various public institutions, and in addition to interviews, surveys will require analysis of various data and statistics.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.5
• /
• pp.1141-1147
• /
• 2017

An unmanned aerial vehicle(UAV), commonly known as a drone, is an aircraft without a human pilot aboard, which is operated by wireless device. A drone provides the capability for the aerial search and traffic control as a police equipment. It has benefits for the missions for the aerial photography with the high resolution camera which can replace eye-dependent search processes. Moreover it has advantage of retrieving several times for the recorded videos. However, if the law enforcement agency misuse and overuse a drone for investigations and search missions without certain regulations and principles, it breaches privacy and personal information infringement. In this paper, we issue a lawful challenges on drone operations and discuss solutions to those challenges.

• Journal of the Korea Society for Simulation
• /
• v.33 no.3
• /
• pp.37-50
• /
• 2024

In indoor disaster scenarios such as fires or gas leak, prompt rescue operations are essential to minimize expected casualties. This paper proposes a simulation model that applies the concept of Manned-Unmanned Teaming (MUM-T) for effective search and rescue in indoor fires. To this end, we first identify appropriate agents to model search and rescue operations. The proposed agent-based simulation consists of a fire and map model, an occupant model, a drone model for occupants searching, a rescuer model for searching and rescuing occupants, and a control center model that assigns missions to drones and rescuers. The agent models identified according to the MUM-T concept interact with other agents during the fire response simulation. Simulation experiments were conducted for search and rescue operations in three scenarios, one consisting of only rescuers and two with mixed rescuers and drones for MUM-T. The simulation results indicated that a drone applied to MUM-T could replace an average of four rescuers. The simulation method proposed in this study is expected to improve the efficiency of search and rescue operations in indoor disaster situations and minimizing the loss of life.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1027-1028
• /
• 2017

드론의 발전 속도는 빠르게 성장하고 있고, 전 세계적으로 방송 촬영, 배송, 구조, 농업분야에서 활용 범위가 확대되고 있다. 본 논문에서의 시스템은 사람이 접근하기 힘든 지역을 간단히 조립하여 수색할 수 있는 스마트 VR 드론을 통해 수색 또는 순찰에 도움이 되고자 한다. 개발된 시스템은 인력과 시간의 제약을 최소화하고, 드론을 통해 촬영한 영상을 사용자에게 가상현실을 이용한 3D영상으로 제공한다.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.159-170
• /
• 2023

It takes a lot of time and manpower to search for the missing. As part of the solution, a missing person search AI system was implemented using a YOLO-based model. In order to train object detection models, the model was learned by collecting recognition images (road fixation) of drone mobile objects from AI-Hub. Additional mountainous terrain datasets were also collected to evaluate performance in training datasets and other environments. In order to optimize the missing person search AI system, performance evaluation based on model size and hyperparameters and additional performance evaluation for concerns about overfitting were conducted. As a result of performance evaluation, it was confirmed that the YOLOv5-L model showed excellent performance, and the performance of the model was further improved by applying data augmentation techniques. Since then, the web service has been applied with the YOLOv5-L model that applies data augmentation techniques to increase the efficiency of searching for missing people.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.321-330
• /
• 2021

By reviewing domestic and international papers, this study examines various fields in which drones are used, and based on the results, fields are suggested in which drones can be used for the work of firefighters. Overall, the research results show that drones are most commonly used for search (51%), disaster and fire monitoring (35%), and delivery (14%). Specifically, in the search field, using a drone is more efficient in terms of manpower, equipment, time, and cost than using people, which is the current practice. Secondly, in disaster and fire monitoring, drones can analyze and identify disasters and fire sites in real time. Therefore, it was confirmed that the use of drones is helpful in securing the safety of firefighters and identifying a disaster site. Third, research in logistics shows that drones can secure the so-called golden time in emergency situations by delivering rescue and relief supplies, emergency medicine, and blood in short order. In a rapidly changing disaster environment, and considering aging in firefighters, this study is meaningful in that it promotes drone utilization in the firefighting field by investigating basic data on drone utilization plans.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.369-370
• /
• 2022

4차 산업혁명이 도래함에 따라서 군사용으로 개발된 드론이 광범위하게 다양한 분야에 활용되어 가고 있다. 드론의 활용으로 이전에 사람이 접근하기 어려웠던 지역이나 현장을 원격탐사 및 데이터 취득이 가능하게 되면서, 도시문제 해결과 재난에 대응할 수 있다. 하지만 기존 드론의 동력원으로 사용하는 리튬폴리머(Li-Po)는 짧은 비행시간 때문에, 재난 현장의 드론 투입에 한계가 있다. 이러한 문제점을 보완하기 위하여 기존 드론 대비 4배 이상 향상된 비행시간을 통해 장기체공이 가능한 액화 수소 드론의 도입이 필요한 것으로 보인다. 늘어난 비행시간과 비가시 장거리 비행 능력을 통해 높은 효율을 낼 수 있는 액화 수소 드론의 활용으로 효과적인 재난 대응 활동에 대한 연구가 필요하다.