• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1475-1490
• /
• 2021

Detecting oil spill area using statistical characteristics of SAR images has limitations in that classification algorithm is complicated and is greatly affected by outliers. To overcome these limitations, studies using neural networks to classify oil spills are recently investigated. However, the studies to evaluate whether the performance of model shows a consistent detection performance for various oil spill cases were insufficient. Therefore, in this study, two CNNs (Convolutional Neural Networks) with basic structures(Simple CNN and U-net) were used to discover whether there is a difference in detection performance according to the structure of CNN and distribution characteristics of oil spill. As a result, through the method proposed in this study, the Simple CNN with contracting path only detected oil spill with an F1 score of 86.24% and U-net, which has both contracting and expansive path showed an F1 score of 91.44%. Both models successfully detected oil spills, but detection performance of the U-net was higher than Simple CNN. Additionally, in order to compare the accuracy of models according to various oil spill cases, the cases were classified into four different categories according to the spatial distribution characteristics of the oil spill (presence of land near the oil spill area) and the clarity of border between oil and seawater. The Simple CNN had F1 score values of 85.71%, 87.43%, 86.50%, and 85.86% for each category, showing the maximum difference of 1.71%. In the case of U-net, the values for each category were 89.77%, 92.27%, 92.59%, and 92.66%, with the maximum difference of 2.90%. Such results indicate that neither model showed significant differences in detection performance by the characteristics of oil spill distribution. However, the difference in detection tendency was caused by the difference in the model structure and the oil spill distribution characteristics. In all four oil spill categories, the Simple CNN showed a tendency to overestimate the oil spill area and the U-net showed a tendency to underestimate it. These tendencies were emphasized when the border between oil and seawater was unclear.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1285-1300
• /
• 2022

Turbidity, the measure of the cloudiness of water, is used as an important index for water quality management. The turbidity can vary greatly in small river systems, which affects water quality in national rivers. Therefore, the generation of high-resolution spatial information on turbidity is very important. In this study, a turbidity retrieval model using the Korea Multi-Purpose Satellite-3 and -3A (KOMPSAT-3/3A) images was developed for high-resolution turbidity mapping of Han River system based on eXtreme Gradient Boosting (XGBoost) algorithm. To this end, the top of atmosphere (TOA) spectral reflectance was calculated from a total of 24 KOMPSAT-3/3A images and 150 Landsat-8 images. The Landsat-8 TOA spectral reflectance was cross-calibrated to the KOMPSAT-3/3A bands. The turbidity measured by the National Water Quality Monitoring Network was used as a reference dataset, and as input variables, the TOA spectral reflectance at the locations of in situ turbidity measurement, the spectral indices (the normalized difference vegetation index, normalized difference water index, and normalized difference turbidity index), and the Moderate Resolution Imaging Spectroradiometer (MODIS)-derived atmospheric products(the atmospheric optical thickness, water vapor, and ozone) were used. Furthermore, by analyzing the KOMPSAT-3/3A TOA spectral reflectance of different turbidities, a new spectral index, new normalized difference turbidity index (nNDTI), was proposed, and it was added as an input variable to the turbidity retrieval model. The XGBoost model showed excellent performance for the retrieval of turbidity with a root mean square error (RMSE) of 2.70 NTU and a normalized RMSE (NRMSE) of 14.70% compared to in situ turbidity, in which the nNDTI proposed in this study was used as the most important variable. The developed turbidity retrieval model was applied to the KOMPSAT-3/3A images to map high-resolution river turbidity, and it was possible to analyze the spatiotemporal variations of turbidity. Through this study, we could confirm that the KOMPSAT-3/3A images are very useful for retrieving high-resolution and accurate spatial information on the river turbidity.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.1
• /
• pp.64-72
• /
• 2009

The method to generate a digital elevation model(DEM) from contour lines causes a problem in which the low relief landform cannot be clearly presented due to the fact that it is significantly influenced by the expression of micro landform elements according to the interval of contours. Thus, this study attempts to develop a landcover burning method that recovers the micro relief landform of the DEM, which applies buffering and map algebra methods by inputting the elevation information to the landcover. In the recovering process of the micro landform, the DEM was recovered using the buffering method and elevation information through the map algebra for the landcover element for the micro landform among the primary DEM generation, making landcover map, and landcover elements. The recovering of the micro landform was applied based on stream landforms. The recovering of landforms using the buffering method was performed for the bar, which is a polygonal element, and wetland according to the properties of concave/convex through generating contours with a uniform interval in which the elevation information applied to the recovered landform. In the case of the linear elements, such as bank, road, waterway, and tributary, the landform can be recovered by using the elevation information through applying a map algebra function. Because the polygonal elements, such as stream channel, river terrace, and artificial objects (farmlands) are determined as a flat property, these are recovered by inputting constant elevation values. The results of this study were compared and analyzed for the degree of landform expression between the original DEM and the recovered DEM. In the results of the analysis, the DEM produced by using the conventional method showed few expressions in micro landform elements. The method developed in this study well described wetland, bar, landform around rivers, farmland, bank, river terrace, and artificial objects. It can be expected that the results of this study contribute to the classification and analysis of micro landforms, plain and the ecology and environment study that requires the recovering of micro landforms around streams and rivers.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.6
• /
• pp.625-633
• /
• 2015

In this study, a coupled probabilistic framework is developed to assess wind risk on apartment buildings by using the convolution of wind hazard and fragility functions. In this framework, typhoon induced extreme wind is estimated by applying the developed Monte Carlo simulation model to the climatological data of typhoons affecting Korean peninsular from 1951 to 2013. The Monte Carlo simulation technique is also used to assess wind fragility function for 4 different damage states by comparing the probability distributions of the window system's resistance performance and wind load. Wind hazard and fragility functions are modeled by the Weibull and lognormal probability distributions based on simulated wind speeds and failure probabilities. The modeled functions are convoluted to obtain the wind risk for the different damage levels. The developed probabilistic framework clearly shows that wind risk are influenced by various important characteristics of terrain and apartment building such as location of building, exposure category, topographic condition, roof angle, height of building, etc. The risk model presented in this paper can be used as tools to predict economic loss estimation and to establish wind risk mitigation plan for the existing building inventory.

• Composites Research
• /
• v.30 no.5
• /
• pp.323-330
• /
• 2017

In this study, multiscale analysis in which the information obtained from molecular dynamics simulation is applied to the continuum mechanics level is conducted to investigate the effects of clustering of silicon carbide nanoparticles reinforced into polypropylene matrix on mechanical behavior of nanocomposites. The elastic behavior of polymer nanocomposites is observed for various states of nanoparticulate agglomeration according to the model reflecting the degradation of interphase properties. In addition, factors which mainly affect the mechanical behavior of the nanocomposites are identified, and new index 'clustering density' is defined. The correlation between the clustering density and the elastic modulus of nanocomposites is understood. As the clustering density increases, the interfacial effect decreased and finally the improvement of mechanical properties is suppressed. By considering the random distribution of the nanoparticles, the range of elastic modulus of nanocomposites for same value of clustering density can be investigated. The correlation can be expressed in the form of exponential function, and the mechanical behavior of the polymer nanocomposites can be effectively predicted by using the nanoparticulate clustering density.

• Journal of Educational Research in Mathematics
• /
• v.26 no.4
• /
• pp.635-662
• /
• 2016

Combinatorics, the basis of probabilistic thinking, is an important area of mathematics and closely linked with other subjects such as informatics and STEAM areas. But combinatorics is one of the most difficult units in school mathematics for leaning and teaching. This study, using the designed combinatorial models and executable expression, aims to analyzes the eye movement of graduate students when they translate the written combinatorial problems to the corresponding executable expression, and examines not only the understanding process of the written combinatorial sentences but also the degree of difficulties depending on the combinatorial semantic structures. The result of the study shows that there are two types of solving process the participants take when they solve the problems : one is to choose the right executable expression by comparing the sentence and the executable expression frequently. The other approach is to find the corresponding executable expression after they derive the suitable mental model by translating the combinatorial sentence. We found the cognitive processing patterns of the participants how they pay attention to words and numbers related to the essential informations hidden in the sentence. Also we found that the student's eyes rest upon the essential combinatorial sentences and executable expressions longer and they perform the complicated cognitive handling process such as comparing the written sentence with executable expressions when they try the problems whose meaning structure is rarely used in the school mathematics. The data of eye movement provide meaningful information for analyzing the cognitive process related to the solving process of the participants.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.5
• /
• pp.19-35
• /
• 2018

The necessity of predicting the spatial information of the site-specific seismic response, which is essential information for the comprehensive earthquake disaster countermeasures, is increasing for the mid-west urban areas where the earthquake-induced damages can be increased due to frequent occurrence of mid-scale earthquake such as 2016 Gyeongju Earthquake and 2017 Pohang Earthquake. Especially, researches on strategic securing of site survey datasets and understanding the site-specific site response characteristics were conducted for Gyeonggi-do, South Korea. In this study, a GIS-based framework for site-specific assessment of site response and induced vulnerable area in Gyeonggi-do, South Korea was proposed. Geo-Data based on GIS platform was constructed for regional estimation of geotechnical characteristics by collecting borehole and land coverage datasets. And the geo-spatial grid information was developed for deriving spatial distribution of geotechnical layer and site response parameters based on the optimization of the geostatistical interpolation method. Accordingly, base information for Improving earthquake preparedness measures was derived as seismic zonation map with administrative sub-units considering the quantitative site effect of Gyeonggi-do.

• Journal of Wetlands Research
• /
• v.8 no.3
• /
• pp.29-38
• /
• 2006

Digital Elevation Model (DEM) of intertidal flat can be widely used not only for scientific fields, coastal management, fisheries, ocean safety, military, but also for understanding natural and artificial topographic changes of the tidal flat. In this study, we generated DEM of the Ganghwado southern intertidal flat, the largest tidal flat in the west coast of the Korean Peninsula, using waterline method and interferometric synthetic aperture radar (InSAR). Constructed DEM which applied waterline method to the Landsat-5 TM and Landsat-7 ETM+ images closely expresses overall topographic relief of tidal flat. We found that the accuracy was determined by the number of waterlines which reflect various tidal conditions. The application of InSAR to the ERS-1/2 and ENVISAT images showed that only ERS-1/2 tandem pairs successfully generated DEM in the part of northern Yeongjongdo, but construction of DEM in the other areas was difficult due to the low coherence caused by a lot of surface remnant waters. In the near future, Kompsat-2 will provide satellite images having multi-spectral and high spatial resolution within a relatively short period at different sea levels. Application of waterline method to these images will help us construct a high precision tidal flat DEM. Also, we should develop DEM generation method using single-pass microwave satellite images.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.581-593
• /
• 2006

Various geological thematic maps have been generated by interpolating sparsely sampled ground survey data and geostatistical kriging that can consider spatial correlation between neighboring data has widely been used. This paper applies multi-variate geostatistical algorithms to integrate secondary information with sparsely sampled ground survey data for geological thematic mapping. Simple kriging with local means and kriging with an external drift are applied among several multi-variate geostatistical algorithms. Two case studies for spatial mapping of groundwater level and grain size have been carried out to illustrate the effectiveness of multi-variate geostatistical algorithms. A digital elevation model and IKONOS remote sensing imagery were used as secondary information in two case studies. Two multi-variate geostatistical algorithms, which can account for both spatial correlation of neighboring data and secondary data, showed smaller prediction errors and more local variations than those of ordinary kriging and linear regression. The benefit of applying the multi-variate geostatistical algorithms, however, depends on sampling density, magnitudes of correlation between primary and secondary data, and spatial correlation of primary data. As a result, the experiment for spatial mapping of grain size in which the effects of those factors were dominant showed that the effect of using the secondary data was relatively small than the experiment for spatial mapping of groundwater level.