• ETRI Journal
• /
• v.45 no.5
• /
• pp.811-821
• /
• 2023

We propose an adaptive unmanned aerial vehicle (UAV)-assisted object recognition algorithm for urban surveillance scenarios. For UAV-assisted surveillance, UAVs are equipped with learning-based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self-adaptive control strategy to maximize the time-averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real-world data demonstrate that the proposed algorithm achieves the desired performance improvements.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.407-418
• /
• 2018

The frequency and risk of disasters are increasing due to environmental and social factors. In order to respond effectively to disasters that occur unexpectedly, it is very important to quickly obtain up-to-date information about target area. It is possible to intuitively judge the situation about the area through the image-map generated at high speed, so that it can cope with disaster quickly and effectively. In this study, we propose an image-map generation and visualization system from UAV images for real-time disaster monitoring. The proposed system consists of aerial segment and ground segment. In the aerial segment, the UAV system acquires the sensory data from digital camera and GPS/IMU sensor. Communication module transmits it to the ground server in real time. In the ground segment, the transmitted sensor data are processed to generate image-maps and the image-maps are visualized on the geo-portal. We conducted experiment to check the accuracy of the image-map using the system. Check points were obtained through ground survey in the data acquisition area. When calculating the difference between adjacent image maps, the relative accuracy was 1.58 m. We confirmed the absolute accuracy of the image map for the position measured from the individual image map. It is confirmed that the map is matched to the existing map with an absolute accuracy of 0.75 m. We confirmed the processing time of each step until the visualization of the image-map. When the image-map was generated with GSD 10 cm, it took 1.67 seconds to visualize. It is expected that the proposed system can be applied to real - time monitoring for disaster response.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.1
• /
• pp.47-54
• /
• 2017

Recently, there are many studies related aerial mapping project and 3 dimensional shape and model reconstruction using UAV(unmanned aerial vehicle) system and images. In this study, we create 3D reconstruction point data using image matching technology of the UAV overlap images, detect shape change of structure and perform accuracy assessment of area($m^2$) and volume($m^3$) value. First, we build the test structure model data and capturing its images of shape change Before and After. Second, for post-processing the Before dataset is convert the form of raster format image to ensure the compare with all 3D point clouds of the After dataset. The result shows high accuracy in the shape change of more than 30 centimeters, but less is still it becomes difficult to apply because of image matching technology has its own limits. But proposed methodology seems very useful to detect illegal any structures and the quantitative analysis of the structure's a certain amount of damage and management.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.1
• /
• pp.139-145
• /
• 2006

The advantage of the lidar data is in fast acquisition and process time as well as in high accuracy and high point density. However lidar data itself is difficult to classify the earth surface because lidar data is in the form of irregularly distributed point clouds. In this study, we investigated land cover classification using both lidar data and optical image through a supervised classification method. Firstly, we generated 1m grid DSM and DEM image and then nDSM was produced by using DSM and DEM. In addition, we had made intensity image using the intensity value of lidar data. As for optical images, the red, blue, green band of CCD image are used. Moreover, a NDVI image using a red band of the CCD image and infrared band of IKONOS image is generated. The experimental results showed that land cover classification with lidar data and optical image together could reach to the accuracy of 74.0%. To improve classification accuracy, we further performed re-classification of shadow area and water body as well as forest and building area. The final classification accuracy was 81.8%.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.3
• /
• pp.317-325
• /
• 2021

Pine wilt disease first appeared in Busan in 1998; it is a serious disease that causes enormous damage to pine trees. The Korean government enacted a special law on the control of pine wilt disease in 2005, which controls and prohibits the movement of pine trees in affected areas. However, existing forecasting and control methods have physical and economic challenges in reducing pine wilt disease that occurs simultaneously and radically in mountainous terrain. In this study, the authors present the use of a deep learning object recognition and prediction method based on visual materials using an unmanned aerial vehicle (UAV) to effectively detect trees suspected of being infected with pine wilt disease. In order to observe pine wilt disease, an orthomosaic was produced using image data acquired through aerial shots. As a result, 198 damaged trees were identified, while 84 damaged trees were identified in field surveys that excluded areas with inaccessible steep slopes and cliffs. Analysis using image segmentation (SegNet) and image detection (YOLOv2) obtained a performance value of 0.57 and 0.77, respectively.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.21 no.4
• /
• pp.65-73
• /
• 2018

Although the road construction in forest is increasing and there is a need for development ecological restoration on deforest area, no consideration has been given to individual trees in there. This study analyzed aerial photographs of deforest area before and after road construction for determining the degree of forest destruction by extracting individual trees. Study area was selected in the sites where are damaged by road construction in GongJu-si, YuSung-gu, and YeongDong-gun. The aerial photograph taken 1979 before construction is panchromatic image of 80cm in GSD (Ground Sample Distance) and other photograph taken 2016 after construction is multi-spectral image of 10cm in GSD. In order to minimize the difference of GSD, we conducted image re-sampling process for setting to same GSD for the two photographs. After that we carried out visual interpretation method for determining to change of individual tree. The result found that for GongJu-si of the number of individual tree was 1,014 in 1979 and 886 in 2016, which decreased by 128 (12.6%) and the average width of those decreased from 5.77m to 5.75m by 0.47%. In case of YoungDong-gun, the number of it was 761 in 1979 and 746 in 2016, which decreased by 2.0% and the average width of it decreased from 8.99mm to 8.90m by 1.1%. Lastly in case of YuSung-gu, the number of it was 1,578 in 1979 and 988 in 2016, which decreased by 37.4% and the average width of it decreased from 7.09m to 6.65m by 6.21%. these result imply that road construction causes destruction of forests. Since there are limitations such as errors due to researcher, it is necessary to construct a quantitative analysis method for the change of the deforest area. It is need to study the method of extracting individual tree in deforest area more accurately using high-resolution image of GSD 10cm or more as well. This study can be used as a basic data for the ecological restoration of the deforest area considering characteristics of individual tree such as height, diameter at breast height, and biomass.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.568-573
• /
• 2018

UAV(Unmanned Aerial Vehicle) is widely used in space information construction, agriculture, fisheries, weather observation, communication, and entertainment fields because they are cheaper and easier to operate than manned aircraft. In particular, UAV have attracted much attention due to the speed and cost of data acquisition in the field of spatial information construction. However, ortho image images produced using UAVs are distorted in buildings and forests. It is necessary to solve these problems in order to utilize the geospatial information field. In this study, fixed wing, rotary wing, vertical take off and landing type UAV were used to detect distortions of ortho image of UAV under various conditions, and various object areas such as construction site, urban area, and forest area were captured and analysed. Through the research, it was found that the redundancy of the unmanned aerial vehicle image is the biggest factor of the distortion phenomenon, and the higher the flight altitude, the less the distortion phenomenon. We also proposed a method to reduce distortion of orthoimage by lowering the resolution of original image using DTM (Digital Terrain Model) to improve distortion. Future high-quality unmanned aerial vehicles without distortions will contribute greatly to the application of UAV in the field of precision surveying.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.181-185
• /
• 2009

In this paper, we are concerned with a 3D line segment extraction method by area-based stereo matching technique. The main idea is based on line fitting of elevation data on 2D line coordinates of ortho-image. Elevation data and ortho-image can be obtained by well-known area-based stereo matching technique. In order to use elevation in line fitting, the elevation itself should be reliable. To measure the reliability of elevation, in this paper, we employ the concept of self-consistency. We test the effectiveness of the proposed method with a quantitative accuracy analysis using synthetic images generated from Avenches data set of Ascona aerial images. Experimental results indicate that our method generates 3D line segments almost 7.5 times more accurate than raw elevations obtained by area-based method.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.6
• /
• pp.63-76
• /
• 2019

UAVs are unmanned, autonomous or remotely piloted aircraft. As UAVs become smaller, lighter and more economical, their applications continue to expand. Researches on UAVs in the field of remote sensing show development methods and purposes similar to those on satellite images, and they are widely used in studies such as 3D image composition and monitoring. In the field of environmental impact assessment(EIA), satellite information and data are mainly used. However, only low-resolution images covering long distances and large-scale data allowing for rough examination are being provided, so their uses are seriously limited. Therefore, in this paper, we construct spatial information of forest area by using unmanned aerial vehicle and seek efficient utilization and policy improvement in the field of environmental impact assessment. As a result, high-resolution images and data from UAVs can be used to identify the location status of SEIA, EIA, and small scale EIA project plans and to evaluate detailed environmental impact analysis. In addition, when provided together with infographics about Post-environmental impact investigation, it was confirmed that the possibility of periodic spatial information construction and evaluation can be used throughout the entire project contents and project post-process.In order to provide sophisticated infographics for the EIA, drone photography and GCP surveying methods were derived.The results of this study will be used as a basis for improving high-resolution monitoring and environmental impact assessment in the forest sector.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.3
• /
• pp.343-350
• /
• 2021

Unmanned aerial vehicles(UAV) photogrammetry provides a cost-effective option for collecting high-resolution 3D point clouds compared with UAV LiDAR and aerial photogrammetry. The main objectives of this study were to (1) validate the accuracy of 3D site model generated, and (2) determine the differences between Digital Elevation Model(DEM) and Digital Surface Model(DSM). In this study, DEM and DSM were shown to have varying degree of accuracy from observed data. The results indicated that the model predictions were considered tend to over- and under-estimated. The range of RMSE of DSM predicted was from 8.2 and 21.3 when compared with the observation. In addition, RMSE values were ranged from 10.2 and 25.8 to compare between DEM predicted and field data. The predict values resulting from the DSM were in agreement with the observed data compared to DEM calculation. In other words, it was determined that the DSM was a better suitable model than DEM. There is potential for enabling automated topography evaluation of the prior-harvest areas by using UAV technology.