• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.275-284
• /
• 2023

Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.

• 한국측량학회지
• /
• 제38권1호
• /
• pp.23-33
• /
• 2020

최근 UAV (Unmanned Aerial Vehicle)를 이용하여 고해상도 영상을 편리하게 취득할 수 있게 되면서 저비용으로 소규모 지역의 관측 및 공간정보 제작이 가능하게 되었다. 특히, 농업환경 모니터링을 위하여 작물생산 지역의 피복지도 생성에 대한 연구가 활발히 진행되고 있으며, 랜덤 포레스트와 SVM (Support Vector Machine) 및 CNN(Convolutional Neural Network) 을 적용하여 분류 성능을 비교한 결과 영상분류에서 딥러닝 적용에 대하여 활용도가 높은 것으로 나타났다. 특히, 위성영상을 이용한 피복분류는 위성영상 데이터 셋과 선행 파라메터를 사용하여 피복분류의 정확도와 시간에 대한 장점을 가지고 있다. 하지만, 무인항공기 영상은 위성영상과 공간해상도와 같은 특성이 달라 이를 적용하기에는 어려움이 있다. 이러한 문제점을 해결하기 위하여 위성영상 데이터 셋이 아닌 UAV를 이용한 데이터 셋과 국내의 소규모 복합 피복이 존재하는 농경지 분석에 활용이 가능한 딥러닝 알고리즘 적용 연구를 수행하였다. 본 연구에서는 최신 딥러닝의 의미론적 영상분류인 DeepLab V3+, FC-DenseNet (Fully Convolutional DenseNets), FRRN-B (Full-Resolution Residual Networks) 를 UAV 데이터 셋에 적용하여 영상분류를 수행하였다. 분류 결과 DeepLab V3+와 FC-DenseNet의 적용 결과가 기존 감독분류보다 높은 전체 정확도 97%, Kappa 계수 0.92로 소규모 지역의 UAV 영상을 활용한 피복분류의 적용가능성을 보여주었다.

• 대한원격탐사학회지
• /
• 제38권6_2호
• /
• pp.1623-1631
• /
• 2022

유출유는 해양 생태계에 큰 위협이 되므로 피해 최소화를 위해 신속한 현황정보파악이 필요하다. 위성원격탐사는 항공기에 비해 광역적 모니터링이 가능하기 때문에 시공간적 범위에서 장점을 가진다. 최근에는 딥러닝 영상인식 기술의 발전으로 인해 딥러닝을 활용한 유출유 탐지의 필요성이 대두되고 있으나, 기존의 Synthetic Aperture Radar (SAR) 영상 위주의 유출유 탐지와는 달리 고해상도 광학영상에 딥러닝 기법을 적용하는 경우는 많지 않았다. 이에, 본 연구에서는 PlanetScope 위성의 광학영상을 활용하여 유출유 레이블을 제작하고, 이를 기반으로 DeepLabV3+모델을 활용하여 유출유 탐지 모델을 구축하였으며, 암맹평가에서 정확도 0.885, 정밀도 0.888, 재현율 0.886, F1점수 0.883, 평균 교집합 대 합집합 비율(Mean Intersection over Union, mIOU) 0.793 등의 상당히 높은 정확도를 나타냈다.

• 한국컴퓨터정보학회논문지
• /
• 제27권9호
• /
• pp.1-12
• /
• 2022

안과 환자의 질병을 판단하기 위해서는 특수 촬영 장비를 통해 찍은 안구영상을 이용한 안과의사의 주관적 판단의 개입이 전통적으로 활용되고 있다. 본 연구에서는 안과 의료진이 질병을 판단할 때 보조적 도움이 될 수 있도록 객관적 진단결과를 제시해주는 각막궤양 의미론적 분할방법에 대하여 제안하였다. 이를 위해 DeepLab 모델을 활용하였고 그 중 Backbone network으로 Xception과 ResNet 네트워크를 이용하였다. 실험결과를 나타내기 위한 평가지표로 다이스 유사계수와 IoU 값을 이용하였고 ResNet101 네트워크를 사용하였을 때 'crop & resized' 이미지에 대해 최대 평균 정확도 93%의 다이스 유사계수 값을 보였다. 본 연구는 객체 검출을 위한 의미론적 분할모델 또한 안구의 각막궤양 부분과 같은 불규칙하고 특이한 모양을 추출하고 분류하는데 뛰어난 결과를 도출할 수 있는 성능을 보유하고 있음을 보여주었다. 향후 학습용 Dataset을 양적으로 보강하여 실험결과의 정확도를 제고할 수 있도록 하고 실제 의료진단 환경에서 구현되어 사용되어 질 수 있도록 할 계획이다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.85-96
• /
• 2023

The number of traffic accidents caused by wet or icy road surface conditions is on the rise every year. Car crashes in such bad road conditions can increase fatalities and serious injuries. Historical data (from the year 2016 to the year 2020) on weather-related traffic accidents show that the fatality rates are fairly high in Korea. This requires accurate prediction and identification of hazardous road conditions. In this study, a forecasting model is developed to predict the chances of traffic accidents that can occur on roads affected by weather and road surface conditions. Multiple deep learning algorithms taking into account AlexNet and 2D-CNN are employed. Data on orthophoto images, automatic weather systems, automated synoptic observing systems, and road surfaces are used for training and testing purposes. The orthophotos images are pre-processed before using them as input data for the modeling process. The procedure involves image segmentation techniques as well as the Z-Curve index. Results indicate that there is an acceptable performance of prediction such as 65% for dry, 46% for moist, and 33% for wet road conditions. The overall accuracy of the model is 53%. The findings of the study may contribute to developing comprehensive measures for enhancing road safety.

• Wind and Structures
• /
• 제36권6호
• /
• pp.405-421
• /
• 2023

Strong wind is the main factors of wind-damage of high-rise buildings, which often creates largely economical losses and casualties. Wind pressure plays a critical role in wind effects on buildings. To obtain the high-resolution wind pressure field, it often requires massive pressure taps. In this study, two traditional methods, including bilinear and bicubic interpolation, and two deep learning techniques including Residual Networks (ResNet) and Generative Adversarial Networks (GANs), are employed to reconstruct wind pressure filed from limited pressure taps on the surface of an ideal building from TPU database. It was found that the GANs model exhibits the best performance in reconstructing the wind pressure field. Meanwhile, it was confirmed that k-means clustering based retained pressure taps as model input can significantly improve the reconstruction ability of GANs model. Finally, the generalization ability of k-means clustering based GANs model in reconstructing wind pressure field is verified by an actual engineering structure. Importantly, the k-means clustering based GANs model can achieve satisfactory reconstruction in wind pressure field under the inputs processing by k-means clustering, even the 20% of pressure taps. Therefore, it is expected to save a huge number of pressure taps under the field reconstruction and achieve timely and accurately reconstruction of wind pressure field under k-means clustering based GANs model.

• Smart Structures and Systems
• /
• 제31권3호
• /
• pp.247-257
• /
• 2023

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRL-based optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.

• 융합신호처리학회논문지
• /
• 제19권2호
• /
• pp.35-41
• /
• 2018

The analysis of plankton species distribution in sea or fresh water is very important in preserving marine ecosystem health. Since manual analysis is infeasible, many automatic approaches were proposed. They usually use images from in situ towed underwater imaging sensor or specially designed, lab mounted microscopic imaging system. Normally they assume that only single plankton is present in an image so that, if there is a clumping among multiple plankton of same species (homogeneous clumping) or if there are multiple plankton of different species scattered in an image (heterogeneous interspersion), they have a difficulty in recognition. In this work, we propose a deep learning based method that can detect and recognize individual plankton in images with homogeneous clumping, heterogeneous interspersion, or combination of both.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• 대한원격탐사학회지
• /
• 제38권6_2호
• /
• pp.1743-1747
• /
• 2022

Sentinel-2는 분광파장대나 공간해상도 측면에서 우리나라 차세대중형위성 4호(농림위성)의 모의영상으로 활용될 수 있다. 이 단보에서는 향후 농림위성영상에 적용하기 위한 예비실험으로, 딥러닝 기술을 이용한 Sentinel-2 영상의 구름탐지를 수행하였다. 전통적인 Convolutional Neural Network (CNN) 모델인 DeepLabV3+와 최신의 Transformer 모델인 Shifted Windows (Swin) Transformer를 이용한 구름탐지 모델을 구축하고, Radiant Earth Foundation (REF)에서 제공하는 22,728장의 학습자료에 대한 암맹평가를 실시하였다. Swin Transformer 모델은 0.886의 정밀도와 0.875의 재현율로, 과탐지와 미탐지가 어느 한쪽으로 치우치지 않는 경향을 보였다. 딥러닝 기반 구름탐지는 향후 우리나라 중심의 실험을 거쳐 농림위성 영상에 활용될 수 있을 것으로 기대된다.