• Economic and Environmental Geology
• /
• v.35 no.1
• /
• pp.67-74
• /
• 2002

The purpose of this study is to determine the weights of the factors for landslide susceptibility analysis using artificial neural network. Landslide locations were identified from interpretation of aerial photographs, field survey data, and topography. The landslide-related factors such as topographic slope, topographic curvature, soil drainage, soil effective thickness, soil texture, wood age and wood diameter were extracted from the spatial database in study area, Yongin. Using these factors, the weights of neural networks were calculated by backpropagation training algorithm and were used to determine the weight of landslide factors. Therefore, by interpreting the weights after training, the weight of each landslide factor can be ranked based on its contribution to the classification. The highest weight is topographic slope that is 5.33 and topographic curvature and soil texture are 1 and 1.17, respectively. Weight determination using backprogpagation algorithms can be used for overlay analysis of GIS so the factor that have low weight can be excluded in future analysis to save computation time.

• Ecology and Resilient Infrastructure
• /
• v.6 no.4
• /
• pp.287-294
• /
• 2019

This study investigated longitudinal changes in riverbed materials properties and temporal alteration of river channel geomorphology in the Geum River basin, where two multipurpose dams(Yongdam Dam and Daecheong Dam) were built in upstream area. We carried out grain size distribution analyses and measured soil organic matter contents of riverbed materials taken at the upper and lower sites of the two large dams. We also estimated the channel width, bar area and vegetation encroachment using the oldest map and aerial photographs taken before and after the construction of the dams. The results can contribute to increasing understandings of dam induced habitat alteration in river ecosystem.

• Journal of Korea Water Resources Association
• /
• v.41 no.12
• /
• pp.1163-1172
• /
• 2008

In this study, area variation, index and degree of alteration, temporal variation of the sandbar and vegetation were analyzed using aerial photographs during the pre and post dam construction at the downstream of dam. Analysis result of the sandbar area was decreased 17 %. Sandbar area was 38 % of the channel areas at the pre dam, but 21 % at the post dam. Alteration indies of the sandbar were $-0.9921{\sim}2.9528$. Analysis result of the vegetation area was increased 13 %. Vegetation area was 11 % of the channel areas at the pre dam, but 24 % at the post dam. Alteration indies of the vegetation were $-0.8908{\sim}12.0736$. Temporal variation of the sandbar and vegetation were analyized at the An Dong dam, Im Ha dam, Hap Chun dam. Analysis result of the sandbar was decreased $42,600m^2$ per year, but vegetation was increased $51,700m^2$ per year. Sandbar area was decreasing more fast than vegetation area increasing.

• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.1 s.9
• /
• pp.71-80
• /
• 1997

This paper suggests a Map Accuracy Standards by analyzing U.S. National Map Accuracy Standards, by considering korean terrain feature and statistical error theory for paper and digital maps on the scale of 1:50,000. Map accuracy standards require horizontal accuracy to be reported as a circular error with 90% confidence level through Linear Error Probable(LEP) theory and Circular Error Probable(CEP) theory. In order to verify the proposed methodology for positioning accuracy testing, several kinds of test point were selected and tested. These test points were extracted at the centers of roads and bridges, the comers of the independent building, the edges of geographical botany, and the tops of mountains. The positioning accuracy assessment was peformed by comparing the positions of test points in digital maps generated three different sources with those acquired by high accurate GPS surveying. The digital maps were produced from aerial photographs and SPOT satellite image using analytical plotter and 1:50,000 paper map.

• Spatial Information Research
• /
• v.6 no.2
• /
• pp.233-245
• /
• 1998

This study focused on developing a comprehensive strategy to revise 1:1,000 digital topographic maps for Seoul metropolitan area in terms of both organizational and technical aspects. First of all, we analyze the elements of' the revision strategy in the organization domain and produce four alternatives. Of these alternatives, we suggest a best alternative which appears to be practically sound. Secondly, we review four possible map updating methodologies, paper map digitization, a partial topographic map revision method, a method utilizing scanned aerial photographs, and a method using digital orthophotos. Through a detailed technical analysis and cost analysis of each method, we suggest a reasonable map updating method. Finally, we provide a guideline for distributing 1:1,000 digital topographic maps based on the digital map distribution policy National Geography Institute.

• Journal of Korean Society of Forest Science
• /
• v.19 no.1
• /
• pp.49-54
• /
• 1973

Surveys of stock volume on steep and vast expanse of mountains, involves various difficulties. And it is extremely uneconomical in forest management point of view, to spend lots of time and man power for surveying such tree volume as the value is much cheaper in comparison with volume and weight. Therefore, a stand volume table estimate easely stock volume per hectare basis from aerial photographs was prepared and correlations to stand volume among factors affecting tree volumation, were studied. Data were 114 places selected from planted Korean white pine, Pinus koreiensis Sieb. et Zucc. stands in Kwangnung Experiment Forest and were computed and analysed by the means of the quantification in the multi-variate statistical analysis. Electronic Data Processing System was applied for data processing at Korean Instiute of Science and Technology. Coefficients of multiple correlations of stand volume table was ranged 0.85~0.88.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.499-506
• /
• 2002

The purpose of this study is to develop landslide susceptibility analysis techniques using artificial neural networks and to apply the newly developed techniques for assessment of landslide susceptibility to the study area of Yongin in Korea. Landslide locations were identified in the study area from interpretation of aerial Photographs and field survey data, and a spatial database of the topography, soil type and timber cover were constructed. The landslide-related factors such as topographic slope, topographic curvature, soil texture, soil drainage, soil effective thickness, timber age, and timber diameter were extracted from the spatial database. Using those factors, landslide susceptibility and weights of each factor were analyzed by two artificial neural network methods. In the first method, the landslide susceptibility index was calculated by the back propagation method, which is a type of artificial neural network method. Then, the susceptibility map was made with a GIS program. The results of the landslide susceptibility analysis were verified using landslide location data. The verification results show satisfactory agreement between the susceptibility index and existing landslide location data. In the second method, weights of each factor were determinated. The weights, relative importance of each factor, were calculated using importance-free characteristics method of artificial neural networks.

• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.1
• /
• pp.47-59
• /
• 2014

This paper deals with a vision-based trajectory tracking control system for a quadrotor-type UAV for entertainment purpose in indoor environment. In contrast to outdoor flights that emphasize the autonomy to complete special missions such as aerial photographs and reconnaissance, indoor flights for entertainment require trajectory following and hovering skills especially in precision and stability of performance. This paper proposes a trajectory tracking control system consisting of a motion generation module, a pose estimation module, and a trajectory tracking module. The motion generation module generates a sequence of motions that are specified by 3-D locations at each sampling time. In the pose estimation module, 3-D position and orientation information of a quadrotor is estimated by recognizing a circular ring pattern installed on the vehicle. The trajectory tracking module controls the 3-D position of a quadrotor in real time using the information from the motion generation module and pose estimation module. The proposed system is tested through several experiments in view of one-point, multi-points, and trajectory tracking control.

• Journal of the Korean Geographical Society
• /
• v.34 no.3
• /
• pp.231-246
• /
• 1999

The geomorphic deformation of the alluvial fans by tectonic movement was investigated along the lineaments of the northern part of the Bulguksa fault system. Based on the aerial photographs interpretation and field surveys Bulguksa fault system was identified as an active reverse fault which has displaced the Quaternary fan deposits. Bulguksa fault system strikes for the direction of NW-SE and N-S. These two lineaments of active fault are crossing at Jinty village in Kyungju city and the fault plane forms here almost vertical dip. Thelateral pressures from the two directions have possibly influenced on the formation of the vertical dip at Jinty village. It should be resulted from that the two pressures responsible for the active reverse fault at which the one with the NW-SE strike thrusts the hanging wall of Tohamsan block southwestward and the other pressure with the N-S jstrike thrusts it westwrd over the foot wall of the fan deposits. The marine oxygen isotope stage 8(0.30-0.25 Ma. BP) and stage 6(0.20-0.14 Ma. BP) are presumed to be the ages of high and middle surfaces of the alluvial fan, repectively. The vertical dispiacements on the high surface along the Bulguksa fault system are about 10.5m at Ha-dong, 9.5-10.5m at Jinhyun-dong, and about 10m at Jinty village. And the vertical displacement on the middle surface was measured about 6m high at Ha-dong. The average slip rate of vertical displacements is calculated about 0.03-0.043mm/y.