• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.1149-1161
• /
• 2021

컴퓨터 비전 기술이 위성영상에 적용되면서, 최근 들어 딥러닝 영상인식을 이용한 구름 탐지가 관심을 끌고 있다. 본연구에서는 SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset과 영상자료증대 기법을 활용하여 U-Net 구름탐지 모델링을 수행하고, 10폴드 교차검증을 통해 객관적인 정확도 평가를 수행하였다. 512×512 화소로 구성된 1800장의 학습자료에 대한 암맹평가 결과, Accuracy 0.821, Precision 0.847, Recall 0.821, F1-score 0.831, IoU (Intersection over Union) 0.723의 비교적 높은 정확도를 나타냈다. 그러나 구름그림자 중 14.5%, 구름 중 19.7% 정도가 땅으로 잘못 예측되기도 했는데, 이는 학습자료의 양과 질을 보다 더 향상시킴으로써 개선 가능할 것으로 보인다. 또한 최근 각광받고 있는 DeepLab V3+ 모델이나 NAS(Neural Architecture Search) 최적화 기법을 통해 차세대중형위성 1, 2, 4호 등의 구름탐지에 활용 가능할 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3364-3382
• /
• 2023

Remote sensing image segmentation plays an important role in realizing intelligent city construction. The current mainstream segmentation networks effectively improve the segmentation effect of remote sensing images by deeply mining the rich texture and semantic features of images. But there are still some problems such as rough results of small target region segmentation and poor edge contour segmentation. To overcome these three challenges, we propose an improved semantic segmentation model, referred to as MRU-Net, which adopts the U-Net architecture as its backbone. Firstly, the convolutional layer is replaced by BasicBlock structure in U-Net network to extract features, then the activation function is replaced to reduce the computational load of model in the network. Secondly, a hybrid multi-scale recognition module is added in the encoder to improve the accuracy of image segmentation of small targets and edge parts. Finally, test on Massachusetts Buildings Dataset and WHU Dataset the experimental results show that compared with the original network the ACC, mIoU and F1 value are improved, and the imposed network shows good robustness and portability in different datasets.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.300-302
• /
• 2022

Palm vein identification has attracted attention due to its distinct characteristics and excellent recognition accuracy. However, many contactless palm vein identification systems suffer from the issue of having low-quality palm images, resulting in degradation of recognition accuracy. This paper proposes the use of U-Net architecture to correctly segment the vascular blood vessel from palm images. Attention gate mechanism and residual block are also utilized to effectively learn the crucial features of a specific segmentation task. The experiments were conducted on CASIA dataset. Hessian-based Jerman filtering method is applied to label the palm vein patterns from the original images, then the network is trained to segment the palm vein features from the background noise. The proposed method has obtained 96.24 IoU coefficient and 98.09 dice coefficient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).

• 스마트미디어저널
• /
• 제13권4호
• /
• pp.86-93
• /
• 2024

기능적 자기 공명영상(functional magnetic resonance imaging;fMRI)의 발전은 뇌 기능의 매핑, 휴식 상태에서 뇌 네트워크의 이해에 상당한 기여를 하였다. 본 논문은 알츠하이머의 진행상태를 분류하기 위해 CNN-LSTM 기반의 분류 모델을 제안한다. 첫 번째로 특징 추출 이전 fMRI 데이터에서 잡음을 제거하기 위해 4단계의 전처리를 수행한다. 두 번째, 전처리가 끝나면 U-Net 구조를 활용하여 공간적 특징을 추출한다. 세 번째, 추출된 공간적 특징은 LSTM을 활용하여 시간적 특징을 추출하여 최종적으로 분류하는 과정을 거친다. 실험은 데이터의 시간차원을 조절하여 진행하였다. 5-fold 교차 검증을 사용하여 평균 96.4%의 정확도를 달성하였고 이러한 결과는 제안된 방법이 fMRI 데이터를 분석하여 알츠하이머의 진행을 식별하는데 높은 잠재력을 가지고 있음을 보여준다.

• 한국의학물리학회지:의학물리
• /
• 제32권4호
• /
• pp.172-178
• /
• 2021

Purpose: This study aimed to develop a deep learning architecture combining two task models to generate synthetic computed tomography (sCT) images from low-tesla magnetic resonance (MR) images to improve metallic marker visibility. Methods: Twenty-three patients with cervical cancer treated with intracavitary radiotherapy (ICR) were retrospectively enrolled, and images were acquired using both a computed tomography (CT) scanner and a low-tesla MR machine. The CT images were aligned to the corresponding MR images using a deformable registration, and the metallic dummy source markers were delineated using threshold-based segmentation followed by manual modification. The deformed CT (dCT), MR, and segmentation mask pairs were used for training and testing. The sCT generation model has a cascaded three-dimensional (3D) U-Net-based architecture that converts MR images to CT images and segments the metallic marker. The performance of the model was evaluated with intensity-based comparison metrics. Results: The proposed model with segmentation loss outperformed the 3D U-Net in terms of errors between the sCT and dCT. The structural similarity score difference was not significant. Conclusions: Our study shows the two-task-based deep learning models for generating the sCT images using low-tesla MR images for 3D ICR. This approach will be useful to the MR-only workflow in high-dose-rate brachytherapy.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제9권2호
• /
• pp.37-44
• /
• 2020

본 논문에서는 딥 러닝 기반의 전-자동 심장 분할 알고리즘을 제안한다. 본 논문에서 제안하는 딥 러닝 모델은 기존 U-Net에 residual recurrent convolutional block과 residual multi-dilated convolutional block을 삽입하여 성능을 개선한 모델이다. 모델의 성능은 테스트 데이터 세트를 전-자동 분할한 결과와 영상의학 전문가의 수동 분할 결과를 비교하여 분석하였다. CT 영상에서 평균 96.88%의 DSC, 95.60%의 precision과 97.00%의 recall 결과를 얻었다. 분할된 영상은 3차원 볼륨 렌더링 기법을 적용하여 시각화한 후 관찰하여 분석할 수 있었다. 실험 결과를 통해 제안된 알고리즘이 다양한 심장 하부 구조를 분할하기에 효과적인 것을 알 수 있었다. 본 논문에서 제안하는 알고리즘이 전문의 또는 방사선사의 임상적 보조역할을 수행할 수 있을 것으로 기대한다.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2276-2282
• /
• 2023

We deploy artificial neural networks to unfold neutron spectra from measured energy-integrated quantities. These neutron spectra represent an important parameter allowing to compute the absorbed dose and the kerma to serve radiation protection in addition to nuclear safety. The built architectures are inspired from convolutional neural networks. The first architecture is made up of residual transposed convolution's blocks while the second is a modified version of the U-net architecture. A large and balanced dataset is simulated following "realistic" physical constraints to train the architectures in an efficient way. Results show a high accuracy prediction of neutron spectra ranging from thermal up to fast spectrum. The dataset processing, the attention paid to performances' metrics and the hyper-optimization are behind the architectures' robustness.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.