• Proceedings of the Korea Water Resources Association Conference
• /
• 2001.05b
• /
• pp.673-678
• /
• 2001

• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.413-413
• /
• 2018

최근 도시지역에 태풍과 집중호우로 인한 홍수발생 빈도와 그 규모가 커지고 있다. 이에 따른 재산 및 인명피해 양상도 매우 심각한 상황이다. 태풍 차바 처럼 강력한 10월 태풍의 출현은 지구 온난화의 전조로 받아들여지고 있다. 또한 10월 태풍임에도 초속 56.5m의 순간 최대풍속과 시간당 최대 116.7mm(제주 서귀포), 139mm(매곡) 등의 강수량은 지역 최대 강수량을 기록함으로써 이제 언제나 태풍 및 홍수에 대한 대비가 필요하게 되었다. 현재 재해에 대비하기 위해 다양한 대책들은 꾸준히 마련되어지고 있으며, 설계 기준 또한 강화되었다. 그러나 저류조 및 배수펌프장 등의 시설물 설치에는 막대한 예산이 필요한데다 장기간의 시간이 필요하며, 비구조적 대책도 마련되어 있으나 태풍 차바의 사례에서 경험한 것처럼 재해 발생 시 대책과 구체적인 방안의 마련이 더욱 시급해 보인다. 이에 본 연구에서는 태풍 차바 시의 호우에 대하여 UNET모형에 의한 부정류모의를 수행하였다. 부정류모의의 경계조건으로써 상류단 경계조건과 측방유입량 조건은 HEC-HMS를 이용하여 유출해석을 실시한 다음 입력 자료로 이용하였으며, 하류단 경계조건으로는 국토부 관할 수위지점의 수위를 이용하여 UNET 모형에 의한 수리학적 하도추적을 수행하였으며, 저지대 침수분석은 지형정보시스템 응용프로그램 중 하나인 ArcGIS를 활용하여 대상유역의 벡터자료를 구축하고 인접도엽의 접합 및 보정을 실시하여 수치고도자료를 생성하여 2차원 홍수범람해석을 위한 HEC-RAS 5.0을 적용하여 침수분석을 수행하였다. 본 연구의 결과를 수재해 피해저감 대책을 수립하는데 기초자료로 활용될 수 있을거라 판단된다.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.390-391
• /
• 2005

• 한국방재학회:학술대회논문집
• /
• 2009.02b
• /
• pp.73.2-73.2
• /
• 2009

• Journal of KIBIM
• /
• v.12 no.1
• /
• pp.55-61
• /
• 2022

Recently, demand for designing own space is increasing as the rapid growth of home furnishing market. However, there is a limitation that it is not easy to compare the style between before construction view and after view. This study aims to translate real image into another style with GAN model learned with interior images. To implement this, first we established style criteria and collected modern, natural, and classic style images, and experimented with ResNet, UNet, Gradient penalty concept to CycleGAN algorithm. As a result of training, model recognize common indoor image elements, such as floor, wall, and furniture, and suitable color, material was converted according to interior style. On the other hand, the form of furniture, ornaments, and detailed pattern expressions are difficult to be recognized by CycleGAN model, and the accuracy lacked. Although UNet converted images more radically than ResNet, it was more stained. The GAN algorithm allowed us to represent results within 2 seconds. Through this, it is possible to quickly and easily visualize and compare the front and after the interior space style to be constructed. Furthermore, this GAN will be available to use in the design rendering include interior.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.18-25
• /
• 2023

In these days, high dimensional data prediction technology based on neural network shows compelling results in many different kind of field including engineering. Especially, a lot of variants of convolution neural network are widely utilized to develop pixel level prediction model for high dimensional data such as picture, or physical field value from the sensors. In this study, velocity vector field of ideal flow on ship surface is estimated on pixel level by Unet. First, potential flow analysis was conducted for the set of hull form data which are generated by hull form transformation method. Thereafter, four different neural network with a U-shape structure were conFig.d to train velocity vectors at the node position of pre-processed hull form data. As a result, for the test hull forms, it was confirmed that the network with short skip-connection gives the most accurate prediction results of streamlines and velocity magnitude. And the results also have a good agreement with potential flow analysis results. However, in some cases which don't have nothing in common with training data in terms of speed or shape, the network has relatively high error at the region of large curvature.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.6 no.3 s.22
• /
• pp.69-76
• /
• 2006

An hydraulic and hydrologic analysis procedure was proposed to reduce the inundation damage of highway in urban stream, that could contribute the EAP and Traffic control planning of Dongbu highway in the Jungrang stream basin which is one of the representative urban area in Korea. We performed the HEC-HMS runoff analysis, and the UNET unsteady flow modeling to decide the inundation reaches and their characteristics. The high inundation risk areas were of Emoon railway bridge and the Wollueng bridge, which are inundated in the case of 10 year and 20 year frequency flood respectively. We also analyze the inundation characteristics under the various conditions of the accumulation rainfall and the duration. Flood elevation at the Wolgye-1 bridge exceed over Risk Flood Water Level(EL.17.84 m) when the accumulation rainfall is over 250 mm and shorter duration than 7 hr. When neglecting backwater effect from the Han river, inundation risk are highly at the reach C2(Wolgye-1 br. ${\sim}$Jungrang br., left bank), C1(Wolgye-1 br. ${\sim}$Jungrang br., right bank), D(Jungrang br. ${\sim}$Gunja br.) in order, but when consider the effect, the inundation risk are higher than the others at the reach D2(Jungrang br. ${\sim}$Gunja br., left bank) and E(Gunja br. ${\sim}$Yongbi br.), which are located downstream near confluence.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.1
• /
• pp.115-127
• /
• 2024

This research aimed to construct models with various structures based on the Transformer module and to perform land cover classification, thereby examining the applicability of the Transformer module. For the classification of land cover, the Unet model, which has a CNN structure, was selected as the base model, and a total of four deep learning models were constructed by combining both the encoder and decoder parts with the Transformer module. During the training process of the deep learning models, the training was repeated 10 times under the same conditions to evaluate the generalization performance. The evaluation of the classification accuracy of the deep learning models showed that the Model D, which utilized the Transformer module in both the encoder and decoder structures, achieved the highest overall accuracy with an average of approximately 89.4% and a Kappa coefficient average of about 73.2%. In terms of training time, models based on CNN were the most efficient. however, the use of Transformer-based models resulted in an average improvement of 0.5% in classification accuracy based on the Kappa coefficient. It is considered necessary to refine the model by considering various variables such as adjusting hyperparameters and image patch sizes during the integration process with CNN models. A common issue identified in all models during the land cover classification process was the difficulty in detecting small-scale objects. To improve this misclassification phenomenon, it is deemed necessary to explore the use of high-resolution input data and integrate multidimensional data that includes terrain and texture information.