• The Journal of Engineering Geology
• /
• v.28 no.4
• /
• pp.701-714
• /
• 2018

The purpose of this study is to show the possibility of 3-dimensional modeling of open-pit limestone mine by using a rotary-wing unmanned aerial vehicle, a drone, and to estimate the amount of mining before and after mining of limestone by explosive blasting. Analysis of the image duplication of the mine has shown that it is possible to achieve high image quality. Analysis of each axis error at the shooting position after analyzing the distortions through camera calibration was shown the allowable range. As a result of estimating the amount of mining before and after explosive blasting, it was possible to estimate the amount of mining of a wide range quickly and accurately in a relatively short time. In conclusion, it is considered that the drone of a rotary-wing unmanned aerial vehicle can be usefully used for the monitoring of open-pit limestone mines and the estimation of the amount of mining. Furthermore, it is expected that this method will be utilized for periodic monitoring of construction sites and road slopes as well as open-pit mines in the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.203-209
• /
• 2021

With the recent development of satellite sensor technology, high-spatial-resolution imagery of various spectral wavelength bands have become possible. Worldview-3 satellite sensor provides panchromatic images with high-spatial-resolution and VNIR (Visible Near InfraRed) and SWIR (ShortWave InfraRed) bands with low-spatial-resolution, so it can be used in various fields such as defense, environment, and surveying. In this study, mineral detection was performed using Worldview-3 satellite imagery. In order to effectively utilize the VNIR and SWIR bands of the Worldview-3 satellite image, the sharpening technique was applied to the spatial resolution of the panchromatic image. To confirm the utility of SWIR bands for mineral detection, mineral detection using only VNIR bands was performed and comparatively evaluated. As the mineral detection technique, SAM (Spectral Angle Mapper), a representative similarity technique, was applied, and the pixels detected as minerals were selected by applying an empirical threshold to the analysis result. Quantitative evaluation was performed using reference data on the results of similarity analysis to evaluate the accuracy of mineral detection. As a result of the accuracy evaluation, the detection rate and false detection rate of mineral detecting using SWIR bands were calculated to be 0.882 and 0.011, respectively, and the results using only VNIR bands were 0.891 and 0.037, respectively. It was found that the detection rate when the SWIR bands were additionally used was lower than that when only the VNIR bands were used. However, it was found that the false detection rate was significantly reduced, and through this, it was possible to confirm the applicability of SWIR bands in mineral detection.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.1
• /
• pp.15-22
• /
• 2022

In order to improve the accuracy of the deep learning object detection technique, the effect of magnification rate conditions and seasonal factors on detection accuracy in aerial photographs and drone images was analyzed through experiments. Among the deep learning object detection techniques, Mask R-CNN, which shows fast learning speed and high accuracy, was used to detect the vehicle to be detected in pixel units. Through Seoul's aerial photo service, learning images were captured at different screen magnifications, and the accuracy was analyzed by learning each. According to the experimental results, the higher the magnification level, the higher the mAP average to 60%, 67%, and 75%. When the magnification rates of train and test data of the data set were alternately arranged, low magnification data was arranged as train data, and high magnification data was arranged as test data, showing a difference of more than 20% compared to the opposite case. And in the case of drone images with a seasonal difference with a time difference of 4 months, the results of learning the image data at the same period showed high accuracy with an average of 93%, confirming that seasonal differences also affect learning.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.2
• /
• pp.291-298
• /
• 2022

Recently developed drones are inexpensive and very convenient to operate. As a result, the production and utilization of spatial information using drones are increasing. However, most drones acquire images with a low-cost global navigation satellite system (GNSS) and an inertial measurement unit (IMU). Accordingly, the accuracy of the initial location and rotation angle elements of the image is low. In addition, because these drones are small and light, they can be greatly affected by wind, making it difficult to maintain a certain overlap, which degrades the positioning accuracy. Therefore, in this study, images are taken at different times in order to analyze the positioning accuracy according to changes in certain exterior orientation parameters. To do this, image processing was performed with Pix4D Mapper and the accuracy of the results was analyzed. In order to analyze the variation of the accuracy according to the exterior orientation parameters in detail, the exterior orientation parameters of the first processing result were used as meta-data for the second processing. Subsequently, the amount of change in the exterior orientation parameters was analyzed by in a strip-by-strip manner. As a result, it was proved that the changes of the Omega and Phi values among the rotation elements were related to a decrease in the height accuracy, while changes in Kappa were linked to the horizontal accuracy.

• 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.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1221-1229
• /
• 2020

In urgent situations such as disasters and accidents, rapid data acquisition and processing is required. Therefore, in this study, a rapid geocoding method according to EOP (Exterior Orientation Parameter) correction was proposed through pattern analysis of the initial UAV image information. As a result, in the research area with a total flight length of 1.3 km and a width of 0.102 ㎢, the generation time of geocoding images took about 5 to 10 seconds per image, showing a position error of about 8.51 m. It is believed that the use of the rapid geocoding method proposed in this study will help provide basic data for on-site monitoring and decision-making in emergency situations such as disasters and accidents.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.79-86
• /
• 2020

Purpose: In this study, a model was developed to estimate the storage in Cheonan reservoir using images taken by Sentinel-1 satellite. Method: A total of three reservoirs were studied. All three reservoirs are small reservoirs whose water level is being measured. The preprocessing of Sentinel-1 images was done using SNAP distributed by the European Space Agency(ESA), and the storage was estimated by classifying water surface by the threshold classification method. The estimated reservoir area was compared with satellite and drones images taken on the same day. The correlation was derived by comparing the estimated reservoir area with the actual measurement. Results and Conclusions: The storage values estimated by satellite image analysis showed similar values to the actual measurement data. However, because of the underestimation of the reservoir area due to green algae and Epilithic diatom of summer reservoirs and the low resolution of satellite images, it is dificult to detect reservoir area by satellite images less than 10,000㎡.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.92-100
• /
• 2020

Currently, the demand for underwater or underwater photography is growing very fast. Its coverage of underwater shooting for broadcasting, leisure and sports, and military and operational use is also growing rapidly. Among them, we specifically select the best camera to be used in underwater drones to photograph and inspect marine life attached to the ship's hull. To compare three cameras performance, they are compared and evaluated using objective and subjective criteria in special circumstances such as underwater shooting. This study checks whether performance criteria, such as resolution of a camera, meet objective and subjective standards in the unusual situation of underwater shooting. And it shows that in addition to the filter that calibrates the image, proper camera selection is important for providing good picture quality. Even after this study, research using more diverse cameras could provide an appropriate standard for comparison of underwater camera quality.

• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.517-526
• /
• 2017

In this study, we analyzed the accuracy of elevation, slope, and area to the damage scale of the debris flow using the drones to track the details of the debris flow that method was between the digital topographical map(1/5,000) method and GPS ground survey method. The results are summarized as follows. At first, in the comparison of elevation, the value by the drones was 3.024m lower than the digital topography map, but in case of slope the average slope was $1.20^{\circ}$ and the maximum slope was $10.46^{\circ}$ which was higher by the drones image. Secondly, the difference area is $462m^2$ between on the digital topographic map and the drones image was calculated high, because it is determined by reflecting the uplift of the terrain as a point that calculated more accurate than the digital topographic map. Therefore, when compared with the existing method, the drone image method was very effective in terms of time and manpower.