• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.425-431
• /
• 2017

As drones gain more popularity these days, drone detection becomes more important part of the drone systems for safety, privacy, crime prevention and etc. However, existing drone detection systems are expensive and heavy so that they are only suitable for industrial or military purpose. This paper proposes a novel approach for training Convolutional Neural Networks to detect drones from images that can be used in embedded systems. Unlike previous works that consider the class probability of the image areas where the class object exists, the proposed approach takes account of all areas in the image for robust classification and object detection. Moreover, a novel loss function is proposed for the CNN to learn more effectively from limited amount of training data. The experimental results with various drone images show that the proposed approach performs efficiently in real drone detection scenarios.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.327-332
• /
• 2023

On December 26, 2022, North Korea's drone provocation resumed for the first time in eight years. The threat covered not only the Seoul metropolitan area but also the no-fly zone for the presidential office's security, and the South Korean military's response to it is not appropriate, which is a major controversy. In the midst of this, problems caused by the prohibition of small drones' flight and illegal intrusion into restricted areas are increasing in Korea, and the threat is becoming a reality, such as being used for terrorist attacks abroad. In this paper, the concept of "Counter-Drone" and related technologies were considered for these drone threats, and implications were derived through domestic and overseas small drone threats, and the direction of development of the Counter-Drone system was presented. North Korea's drone threat is expected to be more diversified, massified, and advanced, resulting in bolder attacks and provocations. Therefore, the South Korean military should push for early powering of the integrated control system and the conter drone system, joint and military cooperation in response to the threat of small drones, and the ability to carry out joint operations between South Korea and the U.S.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.927-934
• /
• 2017

As the technology of drone develops, the use of drone is increasing, In addition, the types of sensors that are inside of smart phones are becoming various and the accuracy is enhancing day by day. Various of researches are being progressed. Therefore, we need to control drone by using smart phone's sensors. In this paper, we propose the most suitable machine learning model that matches the gyro sensor data with drone's moving. First, we classified drone by it's moving of the gyro sensor value of 4 and 8 degree of freedom. After that, we made it to study machine learning. For the method of machine learning, we applied the One-Rule, Neural Network, Decision Tree, and Navie Bayesian. According to the result of experiment that we designated the value from gyro sensor as the attribute, we had the 97.3 percent of highest accuracy that came out from Naive Bayesian method using 2 attributes in 4 degree of freedom. On and the same, in 8 degree of freedom, Naive Bayesian method using 2 attributes showed the highest accuracy of 93.1 percent.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.26 no.2
• /
• pp.230-237
• /
• 2017

Various drones have extended application area very fast. In this paper, we define two contradictions in designing a portable-size drone by using TRIZ technique. The first is a physical contradiction between high rigidity and good portability, and the second is a technical contradiction between high stability and good portability. Through TRIZ technique, six design principles, which guide direction for optimal design, were driven. Consequently, an umbrella mechanism and design criteria were proposed for a portable-size drone. Detail design is verified through finite element method. Test results for the portable-size prototype drone show good performance, and prove its usefulness to be equivalent to a general full-size drone.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.1
• /
• pp.179-185
• /
• 2017

Communication technologies hold a significant place in the swarm flight of drones for surveillance, inspection of disasters and calamities, entertainment performances, and drone collaborations. A GCS(ground control station) for the control of drone swarms needs its devoted communication method to control a large number of drones at the same time. General drone controllers control drones by connecting transmitters and drones in 1:1. When such an old communication method is employed to control many drones simultaneously, problems can emerge with the control of many transmitter modules connected to a GCS and frequency interference among them. This study implemented a transmitter controller to control many drones simultaneously with a communication chip of 2.4GHz ISM band and a Cortex M4-based board. It also designed a GCS to control many transmitter controllers via a network. The hierarchical method made it possible to control many more drones. In addition, the problem with frequency interference was resolved by implementing a time- and frequency-sharing method, controlling many drones simultaneously, and adding the frequency hopping feature. If PPM and S.BUS protocol features are added to it, it will be compatible with more diverse transmitters and drones.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.163-169
• /
• 2021

In this paper, we implemented a deep learning-based automatic object tracking and handy motion control drone system and analyzed the performance of the proposed system. The drone system automatically detects and tracks targets by analyzing images obtained from the drone's camera using deep learning algorithms, consisting of the YOLO, the MobileNet, and the deepSORT. Such deep learning-based detection and tracking algorithms have both higher target detection accuracy and processing speed than the conventional color-based algorithm, the CAMShift. In addition, in order to facilitate the drone control by hand from the ground control station, we classified handy motions and generated flight control commands through motion recognition using the YOLO algorithm. It was confirmed that such a deep learning-based target tracking and drone handy motion control system stably track the target and can easily control the drone.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.969-974
• /
• 2021

South Korea is making efforts to select a drone industry, a type of unmanned aerial vehicle, as one of the 7 major industries in the country, to select a drone-specific liberalization zone and to establish and revise a drone-related bill. Through these efforts, drone delivery and drone taxis are expected to be operated in the future. Therefore, a multilateral collision avoidance system with existing aircraft such as drones, fixed-wing and rotary-wing should be established to prepare for possible drone and air-borne collisions.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1178-1183
• /
• 2021

Based on the camera movement on image expression and grammar, this study intended to analyze the characteristics of image expression filmed and broadcasted by drones. This study analyzed drone images using the movement characteristics of existing video cameras as a coding nomenclature. These were intended to examine the differences from existing video grammar and their implications. This study conducted a content analysis using the entire population of drone news footage broadcast for four years in 2015, 2016, 2017 and 2018 by TV Chosun. The size of the screen, camera work, duration of the shot, camera angle, etc. were selected and analyzed. As a result, the drone camera work showed that it uses the most dolly shots in the case of camera movement, followed by the drone camera movement in the order of pan and tilt shots. For zoom, the frequency of use was the smallest. In addition, this study analyzed the size of the screen, duration of the shot, and camera angle of drone. Analysis shows that drones use certain camera movements most frequently, and unlike grandiose modifiers such as "extension of human gaze," drone remains as a supplementary means to enhance the traditional media expression.

• Journal of Digital Policy
• /
• v.1 no.2
• /
• pp.47-52
• /
• 2022

The absolute dependence on GPS signals for positioning, unstable flight, and short flight time due to battery limitations are the major problems to extend the practical use of drones in the industry. In particular, the short flight time of about 20 minutes is a big issue to the use of drones, and to overcome this, the liquid hydrogen powered drone is being actively developed. However, the revision of the current regulation and certification system for liquid hydrogen powered drone has not been completed yet, making it difficult to test, certify, and commercialize the hydrogen powered drone, which eventually becomes a problem in pre-occupying the increasing drone market. In this paper, we analyze the development trends of hydrogen powered drone and provide the current issues on regulations and certification systems for hydrogen powered drone.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.351-357
• /
• 2022

In this study, a direction for deregulation that can increase the use of drones in the field of spatial information is presented. Regulations and administrative procedures for drone operation showed similar procedures in Japan, the United States, and Korea, such as reporting flight equipment, driver's license, and prohibition of flying within a specific flight zone. In the United States, policies to encourage the use of commercial drones have been implemented, and Japan has slightly tightened regulations on drone operation to protect the Olympics and important national facilities. As a result of the study, in the area where drone operation is restricted for geospatial data construction, Korea was setting the largest area, and GIS analysis showed that Korea's drone flight restricted area was more than 19.4% of the country's land area. In order to increase the utilization of drones in the construction and utilization of spatial information in the future, it is necessary to reset the drone flight restriction zone and reduce the area of the drone flight restriction zone. In addition, it was found that Korea is the only country that has formal and specific regulations on geospatial information security management. In order to increase the construction of geospatial information using drones, it is necessary to ease GSD (Ground Sample Distance)regulations.