• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• Journal of Korea Water Resources Association
• /
• v.54 no.3
• /
• pp.181-190
• /
• 2021

In this study, a large-scale levee breach experiment from lateral overflow was conducted to verify the effect of the new reinforcement method applied to the levee's surface. The new method could prevent levee failure and minimize damage caused by overflow in rivers. The levee was designed at the height of 2.5 m, a length of 12 m, and a slope of 1:2. A new material mixed with biopolymer powder, water, weathered granite, and loess in an appropriate ratio was sprayed on the levee body's surface at a thickness of about 5 cm, and vegetation recruitment was also monitored. At the Andong River Experiment Center, a flow (4 ㎥/s) was introduced from the upstream of the A3 channel to induce the lateral overflow. The change of lateral overflow was measured using an acoustic doppler current profiler in the upstream and downstream. Additionally, cameras and drones were used to analyze the process of the levee breach. Also, a new method using 3D point cloud for calculating the surface loss rate of the levee over time was suggested to evaluate the performance of the levee reinforcement method. It was compared to existing method based on image analysis and the result was reasonable. The proposed 3D point cloud methodology could be a solution for evaluating the performance of levee reinforcement methods.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.3
• /
• pp.41-54
• /
• 2024

Regular monitoring plays a crucial role in ensuring the safety of geotechnical structures. Currently, nondestructive methods are employed to monitor such structures to minimize the impact, e.g., sensor-based accelerometers, displacement meters, image-based lasers, and drone imaging. These technologies can observe surface changes; however, they frequently suffer difficulties in terms of identifying changes in internal properties. To monitor changes in internal properties, in situ geotechnical investigations can be employed. A nondestructive test that can be used for this purpose is the spectral analysis of surface wave (SASW) test using geophones. The SASW test is a nondestructive method; however, due to the time required for data interpretation and the difficulty in analyzing the data, it is challenging to use the SASW test for monitoring applications that require frequent observations. However, it is possible to apply the first-step analysis, which yields the dispersion curve, for monitoring rather than the complete SASW analysis, which yields the shear wave velocity. Thus, this paper presents a fundamental study on the phase difference that derives the dispersion curve to utilize the SASW test for monitoring. The reliability of each phase difference interval is examined to determine the boundary to the subjected monitor. The study used phase difference data obtained using a geophone from a single-layered, homogeneous ground site to evaluate reliable boundaries. The findings of this study are expected to improve the utility of monitoring by identifying the ideal boundary for phase difference data.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.155-163
• /
• 2019

This paper proposes a new methodology to recognize cracks on asphalt road surfaces using the image data obtained with drones. The target section was Yuseong-daero, the main highway of Daejeon. Furthermore, two object detection algorithms, such as Tiny-YOLO-V2 and Faster-RCNN, were used to recognize cracks on road surfaces, classify the crack types, and compare the experimental results. As a result, mean average precision of Faster-RCNN and Tiny-YOLO-V2 was 71% and 33%, respectively. The Faster-RCNN algorithm, 2Stage Detection, showed better performance in identifying and separating road surface cracks than the Yolo algorithm, 1Stage Detection. In the future, it will be possible to prepare a plan for building an infrastructure asset-management system using drones and AI crack detection systems. An efficient and economical road-maintenance decision-support system will be established and an operating environment will be produced.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.12-21
• /
• 2019

In the era of the Fourth Industrial Revolution, drones have become a flexible device that can be integrated with new technologies. The drones were originally developed as military unmanned aircraft and are now being used in various fields. In the environment and weather observation area, the atmospheric boundary layer is near the surface where the atmosphere is the most active in the meteorological phenomenon and has a close influence on human activities. In order to carry out the study of these atmospheric boundary layers, it is necessary to observe precisely the lower atmosphere and secure the observation technology. The drones in the meteorological field can be used for meteorological observations at a relatively low maintenance cost compared to existing equipment. When used in conjunction with various sensors, the drones can be widely used in atmospheric boundary layer and local meteorological studies. In this study, the possibility of meteorological observations using drones was confirmed by conducting vertical meteorological (temperature and humidity) observation experiments equipped with a combined meteorological sensor and a radio sonde on drones owned by NIMS.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.69-69
• /
• 2017

최근 여러 분야에서 드론에 대한 관심도가 높아짐에 따라, 하천분야에서도 다양한 연구에 드론이 활용하고 있다. 드론관련 기술의 발전으로 GPS와 같은 첨단 기술이 탑재되어 사용자에게 여러가지 정보를 제공하며, 조작 또한 간단하여 누구나 쉽게 활용할 수 있다. 그리고 무엇보다도 사람이 접근하기 힘든 지역을 쉽게 촬영할 수 있다는 큰 장점을 가지고 있다. 본 연구의 목적은 드론을 기반으로 표면영상유속측정법을 적용시켜 하천의 표면유속을 효율적으로 측정하는 것이다. 표면영상유속측정법은 카메라로 촬영된 영상을 이용하여 표면유속을 도출하기 때문에 촬영된 영상이 무엇보다도 중요하다. 하지만 드론으로 촬영된 영상들은 아무리 정지비행을 잘하더라도 필연적으로 영상에 흔들림이 존재한다. 이를 해결하기 위해 본 연구에서는 흔들린 영상에 대하여 형태 정합법에 의해 보정을 하였으며, 이는 가장 핵심적인 기술이라 할 수 있다. 형태 정합법에 의한 영상 보정 과정은 고정된 표정점을 영상에서 추적한 뒤, 기준 영상의 표정점과 보정 영상의 표정점이 일치하도록 보정하였다. 영상 보정 후 영상 처리와 분석프로그램을 통하여 유속을 도출한다. 기존의 표면영상유속측정법에서는 표정점을 설치한 후 각 표정점마다 측량을 실시하여 좌표를 측정하였다. 이는 한국건설기술연구원 안동하천실험센터와 같이 이상적인 실험을 진행할 수 있는 환경에서는 문제가 없다. 하지만 실제 하천에서 표면유속측정 시 하천의 폭, 주변 환경 등의 영향으로 측량작업에 많은 어려움이 있다. 이를 해결하기 위해 본 연구에서는 Arduino와 GPS센서를 이용하여 표정점을 구성하였다. Arduino와 GPS 센서를 이용하면 각 표정점들의 좌표를 노트북에서 실시간으로 자동으로 확인할 수 있다. GPS 센서의 측정 오차에 따라 관측 오차가 다소 존재하지만, 실제 측량을 할 때와는 비교할 수 없을 정도로 신속하게 표정점의 좌표를 구할 수 있다. 이를 바탕으로 실험 하천에 대해 적용한 결과 기존의 방법에 비하여 간편하고 빠르게 표면유속측정을 수행할 수 있었으며, 표면유속측정값 또한 만족스러운 결과를 얻을 수 있었다.

• Nanomaterials
• /
• v.12 no.5
• /
• pp.827-838
• /
• 2022

Controlling the Schottky barrier height (φ_B) and other parameters of Schottky barrier diodes (SBD) is critical for many applications. In this work, the effect of inserting a graphene interfacial monolayer between a Ni Schottky metal and a β-Ga₂O₃ semiconductor was investigated using numerical simulation. We confirmed that the simulation-based on Ni workfunction, interfacial trap concentration, and surface electron affinity was well-matched with the actual device characterization. Insertion of the graphene layer achieved a remarkable decrease in the barrier height (φ_B), from 1.32 to 0.43 eV, and in the series resistance (R_s), from 60.3 to 2.90 mΩ.cm². However, the saturation current (J_s) increased from 1.26×10^-11 to 8.3×10^-7(A/cm²). The effects of a graphene bandgap and workfunction were studied. With an increase in the graphene workfunction and bandgap, the Schottky barrier height and series resistance increased and the saturation current decreased. This behavior was related to the tunneling rate variations in the graphene layer. Therefore, control of Schottky barrier diode output parameters was achieved by monitoring the tunneling rate in the graphene layer (through the control of the bandgap) and by controlling the Schottky barrier height according to the Schottky-Mott role (through the control of the workfunction). Furthermore, a zero-bandgap and low-workfunction graphene layer behaves as an ohmic contact, which is in agreement with published results.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1731-1738
• /
• 2021

The objective of this study was to extract individual trees and tree heights using UAV drone images. The study site was Gongju national university experiment forest, located in Yesan-gun, Chungcheongnam-do. The thinning intensity study sites consisted of 40% thinning, 20% thinning, 10% thinning and control. The image was filmed by using the "Mavic Pro 2" model of DJI company, and the altitude of the photo shoot was set at 80% of the overlay between 180m pictures. In order to prevent image distortion, a ground reference point was installed and the end lap and side lap were set to 80%. Tree heights were extracted using Digital Surface Model (DSM) and Digital Terrain Model (DTM), and individual trees were split and extracted using object-based analysis. As a result of individual tree extraction, thinning 40% stands showed the highest extraction rate of 109.1%, while thinning 20% showed 87.1%, thinning 10% showed 63.5%, and control sites showed 56.0% of accuracy. As a result of tree height extraction, thinning 40% showed 1.43m error compared with field survey data, while thinning 20% showed 1.73 m, thinning 10% showed 1.88 m, and control sites showed the largest error of 2.22 m.

• 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 the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.5
• /
• pp.443-451
• /
• 2015

In photogrammetry, GCPs (Ground Control Points) have traditionally been used to determine EOPs (Exterior Orientation Parameters) and to produce DEM (Digital Elevation Model). The existing DEM can be used as GCPs, where the observer’s approach is a difficult area, because it is very restrictive to survey in the field. For this, DEM matching should be performed. This study proposed the fusion method using ICP (Iterative Closest Point) and RT (proposed method by Rosenholm and Torlegard, 1988) in order to improve accuracy of the DEM matching. The proposed method was compared to the ICP method to evaluate its usefulness. Pseudo reference DEM with resolution 10m, and modified DEM (random-numbers are added from 0 to 2 at height; scale is 0.9; translation is 100 meters in 3-D axes; rotation is from 10° to 50° from the reference DEM) were used in the experiment. The results proposed accuracy was highest in the matching and absolute orientation. In the case of ICP, according to rotation of the modified DEM being increased, absolute orientation error is increased, while the proposed method generally showed consistent results without increasing the error. The proposed method would be applied to matching when the DEM is modified up to 30° rotation, compared to the reference DEM, based on the results of experiments. In addition when we use Drone, this method can be utilized to identify EOPs or detect 3-D surface deformation from the existing DEM of the inaccessible area.