• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.178-179
• /
• 2018

Recently, methods of using machine learning in artificial intelligence such as autonomous navigation and speech recognition have been actively studied. Classical image processing methods such as classical boundary detection and pattern recognition have many limitations in order to recognize a specific object or area in a digital image. However, when a machine learning method such as deep-learning is used, Can be obtained. However, basically, a large amount of learning data must be secured for machine learning such as deep-learning. Therefore, it is difficult to apply the machine learning for area classification when the amount of data is very small, such as aerial photographs for environmental analysis. In this study, we apply a transfer-learning technique that can be used when the dataset size of the input image is small and the shape of the input image is not included in the category of the training dataset.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.145-154
• /
• 2014

The road network becomes more complex and extensive. Therefore, the inconveniences are caused in accordance with the time delay of the restoration of damaged roads, demands for excessive costs on information collection, and limitations on acquisition of damage information of the roads. Recently, road centric spatial information is gathered using mobile multi sensor system for road inventory. But expensive MMS(Mobile Mapping System) equipments require high maintenance costs from beginning and takes a lot of time in the data processing. So research is needed for continuous maintenance by collecting and displaying the damaged information on a digital map using low cost mobile camera system. In this research we aim to develop the techniques for mosaic with a regular ground sample distance using successive image from oblique camera on a vehicle. For doing this, mosaic image is generated by estimating the homography of high resolution oblique image, and the ground sample distance and appropriate overlap are analyzed using high resolution aerial oblique images which contain resolution target. Based on this we have proposed the appropriate overlap and exposure interval for mobile road inventory system.

• 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.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.5
• /
• pp.455-463
• /
• 2008

The shadows, which is generated when acquiring data using optical sensor, mutilates consistency of brightness for same objects in the images. Hence, it makes a trouble to interpret the ground information. This study is focused on detecting the shadowing area in the images. And only single image is used without any other data which is acquired from different source. Also, This study presents the method using HSI color model, especially, using I(intensity) information, and the intensity clustering algorithm. Then, we illuminate the effects of shadow by FFT(Fast Fourier Transform).

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.302-305
• /
• 2004

The aim of this study is to apply and crossvalidate a spatial logistic multiple-regression model at Boun, Korea, using a Geographic Information System (GIS). Landslide locations in the Boun area were identified by interpretation of aerial photographs and field surveys. Maps of the topography, soil type, forest cover, geology, and land-use were constructed from a spatial database. The factors that influence landslide occurrence, such as slope, aspect, and curvature of topography, were calculated from the topographic database. Texture, material, drainage, and effective soil thickness were extracted from the soil database, and type, diameter, and density of forest were extracted from the forest database. Lithology was extracted from the geological database and land-use was classified from the Landsat TM image satellite image. Landslide susceptibility was analyzed using landslide-occurrence factors by logistic multiple-regression methods. For validation and cross-validation, the result of the analysis was applied both to the study area, Boun, and another area, Youngin, Korea. The validation and cross-validation results showed satisfactory agreement between the susceptibility map and the existing data with respect to landslide locations. The GIS was used to analyze the vast amount of data efficiently, and statistical programs were used to maintain specificity and accuracy.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.298-301
• /
• 2004

The aim of this study is to cross-validate of spatial probability model, artificial neural network at Boun, Korea, using a Geographic Information System (GIS). Landslide locations were identified in the Boun, Janghung and Youngin areas from interpretation of aerial photographs, field surveys, and maps of the topography, soil type, forest cover and land use were constructed to spatial data-sets. The factors that influence landslide occurrence, such as slope, aspect and curvature of topography, were calculated from the topographic database. Topographic type, texture, material, drainage and effective soil thickness were extracted from the soil database, and type, diameter, age and density of forest were extracted from the forest database. Lithology was extracted from the geological database, and land use was classified from the Landsat TM image satellite image. Landslide susceptibility was analyzed using the landslide­occurrence factors by artificial neural network model. For the validation and cross-validation, the result of the analysis was applied to each study areas. The validation and cross-validate results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.3
• /
• pp.267-274
• /
• 2009

Recently, UAVs (Unmanned Aerial Vehicles) are expected much as the Unmanned Systems for various missions. These missions are often based on the Vision System. Especially, missions such as surveillance and pursuit have a process which is carried on through the transmitted vision data from the UAV. In case of small UAVs, monocular vision is often used to consider weights and expenses. Research of missions performance using the monocular vision is continued but, actually, ground and target model have difference in distance from the UAV. So, 3D distance measurement is still incorrect. In this study, Mean-Shift Algorithm, Optical Flow and Subspace Method are posed to estimate the relative depth. Mean-Shift Algorithm is used for target tracking and determining Region of Interest (ROI). Optical Flow includes image motion information using pixel intensity. After that, Subspace Method computes the translation and rotation of image and estimates the relative depth. Finally, we present the results of this study using images obtained from the UAV experiments.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.249-256
• /
• 2022

In the case of Drone Photogrammetry, the "pixel to point tool" module of Metashape, Pix4D Mapper, ContextCapture, and Global MapperGIS, which is a simple software, are widely used. Each SW has its own logic for the analysis of aerial triangulation, but from the user's point of view, it is necessary to select a SW by comparative analysis of the coordinate values of geospatial information for the result. Taking aerial photos for drone photogrammetry, surveying GCP reference points through VRS-GPS Survey, processing the acquired basic data using each SW to construct ortho image and DSM, and GCPSurvey performance and acquisition from each SW The coordinates (X,Y) of the center point of the GCP target on the Ortho-Image and the height value (EL) of the GCP point by DSM were compared. According to the "Public Surveying Work Regulations", the results of each SW are all within the margin of error. It turned out that there is no problem with the regulations no matter which SW is included within the scope.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.6
• /
• pp.33-38
• /
• 2016

Understanding of current features of collapsed buildings, terrain, and other infrastructures is a critical issue for disaster site managers. On the other hand, a comprehensive site investigation of current location of survivors buried under the remains of a building is a difficult task for disaster managers due to the difficulties in acquiring the various information on the disaster sites. To overcome these circumstances, such as large disaster sites and limited capability of rescue workers, this study makes use of a drone (unmanned aerial vehicle) to effectively obtain current image data from large disaster areas. The framework of 3D model reconstruction of disaster sites using aerial imagery acquired by drones was also presented. The proposed methodology is expected to assist fire fighters and workers on disaster sites in making a rapid and accurate identification of the survivors under collapsed buildings.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.14 no.4
• /
• pp.65-70
• /
• 2010

A small unmanned aerial vehicle(UAV), which uses a propulsion system consisting of electric motor and battery, weighs less than 8 kg, capable of hand launch. Because it is easy to operate and able to transmit image information in real time, the use of small UAV has been increasing. However, very few analysis methods or analysis results on flight performance of the small UAV have been known so far. In this paper, the performance analysis methods of a small UAV, which is manufactured to study an electric powered UAV, are suggested and their results are achieved. Aerodynamic data of the vehicle are obtained by making use of gliding performance from actual flight test, and required thrust and required power by flight speed are predicted. In addition, the methods to predict range and endurance in case of using battery as power source are suggested and their results are achieved.