• Journal of the Korea Institute of Building Construction
• /
• v.17 no.6
• /
• pp.545-557
• /
• 2017

The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate.

• Journal of Ecology and Environment
• /
• v.41 no.5
• /
• pp.145-151
• /
• 2017

Background: Conventional bird observation methods are line survey or point count method by bare eyes or through binoculars or telescopes. But in this study, the possibility of monitoring waterbirds using drones beyond the conventional research methods was explored. It also describes the direction of producing and accumulating images of waterbird habitats as a method to efficiently determine changes in waterbird habitats. Results: From the study, it was concluded that waterbird monitoring using drones was a new monitoring technique which could be applied to the field and 26 kinds of waterbirds were observed. In the case of a drone with a single lens, it was difficult to identify objects because the size of the subject was too small at a certain altitude. In this case, zoom lens can be an alternative. It has also been verified that image analysis software can be used to accumulate images of waterbird habitats. Conclusions: If various kinds of advanced drones and cameras are used, it would be possible to monitor larger areas including the areas that are difficult for human access and to observe more waterbirds and wider habitats.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.75-80
• /
• 2023

Unmanned drone stations for automatic charging have been developed in order to overcome the flying time limitation of rotary wing drones. Since the drone stations is an unmanned operating system, each of the drones will be required to have a high degree of landing accuracy. Drone precision landing has been mainly studied depended on image processing technologies, but the image processing systems make several problems, such as the mission weight, the drone cost, and the development complexity increases, and the flight time decrease. Thus, this paper researched accuracy of precision landing based on RTK (real time kinetics) for rotary wing drones. For the experiments of RTK based precision landing, a drone repeatedly performed three missions. The survey accuracies of the RTK about missions respectively were set as 0.3, 0.2, and 0.1 meters. Each mission has one take-off point, two way-points and one landing-point, and was repeated ten times. The experiment results revealed landing error distance means of around 0.258, 0.12 and 0.057 meters on each of RTK setting.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.349-350
• /
• 2019

The autonomous driving drones experimented in the existing indoor corridor environment was a way to give the steering command to the drones by the neural network operation of the notebook due to the limitation of the operation performance of the drones. In this paper, to overcome these limitations, we have studied autonomous driving in indoor corridor environment using NVIDIA Jetson TX2 board.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.1
• /
• pp.163-168
• /
• 2018

With the advent of the fourth industrial revolution era, the use of drone has been progressing rapidly in various fields. Now the drones will be used extensively in the area of investigation. Until now the criminal photographs stayed in 2D digital images, it would be possible to reproduce not only 3D images but also make a crime scene with 3D printer. Firstly, the video images taken by the investigation agency using the drones are digital image evidence, and the requirements for securing the evidence capability are not different from the conditions for obtaining the proof of digital evidence. However, when the drones become a new area of scientific investigation, it is essential to systematize the authenticity of the images taken by the drones so that they can be used as evidence. In this paper, I propose a method to secure the evidence capability of digital images taken by drone.

• Journal of Industrial Convergence
• /
• v.18 no.1
• /
• pp.79-85
• /
• 2020

Recently, the RPAS(Remote Piloted Aircraft System), by remote control and autonomous navigation, has been increasing in interest and utilization in various industries and public organizations along with delivery drones, fire drones, ambulances, agricultural drones, and others. The problems of the stability of unmanned drones, which can be self-controlled, are also the biggest challenge to be solved along the development of the drone industry. drones should be able to fly in the specified path the autonomous flight control system sets, and perform automatically an accurate landing at the destination. This study proposes a technique to check arrival by landing point images and control landing at the correct point, compensating for errors in location data of the drone sensors and GPS. Receiving from the Google Map API and learning from the destination video, taking images of the landing point with a drone equipped with a NAVIO2 and Raspberry Pi, camera, sending them to the server, adjusting the location of the drone in line with threshold, Drones can automatically land at the landing point.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.2
• /
• pp.81-91
• /
• 2021

Drone related research has been increasing recently due to the development and distribution of commercial unmanned aerial vehicles. However, most of the previous studies focused on the accuracy and utility of drone surveying. For drones, the resolution of the result is determined according to the flight altitude, but since 70% of Korea is mountainous, it is necessary to analyze the quality of the drone image according to the flight plan. In this study, the quality of drone photogrammetry results according to flight plans was analyzed. The flight plan was established by fixed altitude and considering the height of the terrain. Images were acquired for both cases and data was processed to generate ortho images. As a result of evaluating the accuracy of the generated ortho image, the accuracy was found to be -0.07 ~ 0.09m. The accuracy of Case I and Case II did not show a significant difference, but for RMSE, Case I showed a good value. These results indicate that the drone flight plan affects the quality of the results. Also, when flying at a fixed altitude, II showed a lower value than the originally set overlap according to the altitude of the object. In future surveys using drones, flight planning taking into account the height of the object will contribute to the improvement of the quality of the results.

• 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.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.907-916
• /
• 2020

Images taken from airplanes, satellites and drones have been used in various realms, and the kinds and specifications of images are enlarged gradually. Despite the importance of images on diverse applications, the quality information of the images is controlled by each agency or institute respectively without any principle, or even is neglected, because the application of standards to the final products of image is not easy in Korea. We aim to review necessities and strategies for applying international standards on image and to suggest potential issues and possibilities to make standards in action.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.639-644
• /
• 2024

Recent developments in the use of drones on battlefields, extending beyond reconnaissance to firepower support, have greatly increased the importance of technologies for early automatic drone identification. In this study, to identify an effective image classification model that can distinguish drones from other aerial targets of similar size and appearance, such as birds and balloons, we utilized a dataset of 3,600 images collected from the internet. We adopted a transfer learning approach that combines the feature extraction capabilities of three pre-trained convolutional neural network models (VGG16, ResNet50, InceptionV3) with an additional classifier. Specifically, we conducted a comparative analysis of the performance of these three pre-trained models to determine the most effective one. The results showed that the InceptionV3 model achieved the highest accuracy at 99.66%. This research represents a new endeavor in utilizing existing convolutional neural network models and transfer learning for drone identification, which is expected to make a significant contribution to the advancement of drone identification technologies.