• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1091-1100
• /
• 2022

딥러닝 기술의 진보와 함께 다양한 국내외 고해상도 원격탐사 영상의 활용이 가능함에 따라 딥러닝 기술과 원격탐사 빅데이터를 활용하여 도심 지역 건물 검출과 변화탐지에 활용하고자 하는 관심이 크게 증가하고 있다. 본 논문에서는 고해상도 원격탐사 영상의 의미론적 건물 분할을 위해서 건물 분할에 우수한 성능을 보이는 DeepResUNet 모델을 기본 구조로 하고 잔차 학습 단위를 개선하고 Convolutional Block Attention Module(CBAM)을 결합한 새로운 건물 분할 모델인 CBAM-DRUNet을 제안한다. 제안한 건물 분할 모델은 WHU 데이터셋과 INRIA 데이터셋을 이용한 성능 평가에서 UNet을 비롯하여 ResUNet, DeepResUNet 대비 F1 score, 정확도, 재현율 측면에서 모두 우수한 성능을 보였다.

• 대한원격탐사학회지
• /
• 제35권6_2호
• /
• pp.1053-1065
• /
• 2019

신기후체제에 대응하여 정확한 탄소흡수 및 배출량을 산정하기 위해 토지이용 범주별 통계량 산출은 활동자료로서 매우 중요한 자료이다. 본 연구는 효과적인 토지이용 범주별 판독을 위하여 산림항공사진(이하 FAP)에 딥러닝모델을 적용하여 토지이용 범주별 자동화 판독 분류를 한 후 샘플링기법을 통해 국가단위 통계량을 산출하였다. 딥러닝모델에 적용한 데이터세트(이하, DS)는 국가산림자원조사 고정표본점 위치 기반 FAP의 이미지를 추출하여 훈련데이터세트(이하, 훈련DS)와 시험데이터세트(이하, 시험 DS)로 구분하였다. 훈련 DS는 토지이용 범주별 정의에 따라 이미지별 레이블을 부여하였으며, 딥러닝모델을 학습하고 검증하였다. 검증 시 모델의 학습정확도는 학습 횟수 1500회에서 정확도가 약 89%로 가장 높았다. 학습된 딥러닝모델을 시험DS에 적용한 결과, 이미지 레이블의 판독 분류정확도는 약 90%로 높았다. 샘플링기법을 통해 범주별 분류 결과에 대해 면적을 추정하여 국가통계와 비교한 결과 정합성 또한 높아 향후 LULUCF(Land Use, Land Use Change, Forestry)분야 국가 온실가스 인벤토리 보고서의 활동자료로 활용하기에 충분하다고 판단된다.

• Journal of Animal Science and Technology
• /
• 제66권1호
• /
• pp.167-177
• /
• 2024

Iris segmentation is an initial step for identifying the biometrics of animals when establishing a traceability system for livestock. In this study, we propose a deep learning framework for pixel-wise segmentation of bovine iris with a minimized use of annotation labels utilizing the BovineAAEyes80 public dataset. The proposed image segmentation framework encompasses data collection, data preparation, data augmentation selection, training of 15 deep neural network (DNN) models with varying encoder backbones and segmentation decoder DNNs, and evaluation of the models using multiple metrics and graphical segmentation results. This framework aims to provide comprehensive and in-depth information on each model's training and testing outcomes to optimize bovine iris segmentation performance. In the experiment, U-Net with a VGG16 backbone was identified as the optimal combination of encoder and decoder models for the dataset, achieving an accuracy and dice coefficient score of 99.50% and 98.35%, respectively. Notably, the selected model accurately segmented even corrupted images without proper annotation data. This study contributes to the advancement of iris segmentation and the establishment of a reliable DNN training framework.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• Journal of Forest and Environmental Science
• /
• 제40권1호
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.147-165
• /
• 2021

In this work, we empirically evaluated the efficiency of the recent EfficientNetB0 model to identify and diagnose malaria parasite infections in blood smears. The dataset used was collected and classified by relevant experts from the Lister Hill National Centre for Biomedical Communications (LHNCBC). We prepared our samples with minimal image transformations as opposed to others, as we focused more on the feature extraction capability of the EfficientNetB0 baseline model. We applied transfer learning to increase the initial feature sets and reduced the training time to train our model. We then fine-tuned it to work with our proposed layers and re-trained the entire model to learn from our prepared dataset. The highest overall accuracy attained from our evaluated results was 94.70% from fifty epochs and followed by 94.68% within just ten. Additional visualization and analysis using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm visualized how effectively our fine-tuned EfficientNetB0 detected infections better than other recent state-of-the-art DCNN models. This study, therefore, concludes that when fine-tuned, the recent EfficientNetB0 will generate highly accurate deep learning solutions for the identification of malaria parasites in blood smears without the need for stringent pre-processing, optimization, or data augmentation of images.

• 한국군사과학기술학회지
• /
• 제24권3호
• /
• pp.281-292
• /
• 2021

With the development of deep learning technology, researchers and technicians keep attempting to apply deep learning in various industrial and academic fields, including the defense. Most of these attempts assume that the data are balanced. In reality, since lots of the data are imbalanced, the classifier is not properly built and the model's performance can be low. Therefore, this study proposes cost-sensitive learning as a solution to the imbalance data problem of image classification in the defense field. In the proposed model, cost-sensitive learning is a method of giving a high weight on the cost function of a minority class. The results of cost-sensitive based model shows the test F1-score is higher when cost-sensitive learning is applied than general learning's through 160 experiments using submarine/non-submarine dataset and warship/non-warship dataset. Furthermore, statistical tests are conducted and the results are shown significantly.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.478-480
• /
• 2022

This paper studies human activity image classification using deep transfer learning techniques focused on the inception convolutional neural networks (InceptionV3) model. For this, we used UFC-101 public datasets containing a group of students' behaviors in mathematics classrooms at a school in Thailand. The video dataset contains Play Sitar, Tai Chi, Walking with Dog, and Student Study (our dataset) classes. The experiment was conducted in three phases. First, it extracts an image frame from the video, and a tag is labeled on the frame. Second, it loads the dataset into the inception V3 with transfer learning for image classification of four classes. Lastly, we evaluate the model's accuracy using precision, recall, F1-Score, and confusion matrix. The outcomes of the classifications for the public and our dataset are 1) Play Sitar (precision = 1.0, recall = 1.0, F1 = 1.0), 2), Tai Chi (precision = 1.0, recall = 1.0, F1 = 1.0), 3) Walking with Dog (precision = 1.0, recall = 1.0, F1 = 1.0), and 4) Student Study (precision = 1.0, recall = 1.0, F1 = 1.0), respectively. The results show that the overall accuracy of the classification rate is 100% which states the model is more powerful for learning UCF-101 and our dataset with higher accuracy.

• 한국공간구조학회논문집
• /
• 제24권2호
• /
• pp.91-99
• /
• 2024

In this paper, machine learning models were applied to predict the seismic response of steel frame structures. Both geometric and material nonlinearities were considered in the structural analysis, and nonlinear inelastic dynamic analysis was performed. The ground acceleration response of the El Centro earthquake was applied to obtain the displacement of the top floor, which was used as the dataset for the machine learning methods. Learning was performed using two methods: Decision Tree and Random Forest, and their efficiency was demonstrated through application to 2-story and 6-story 3-D steel frame structure examples.