期刊
JOURNAL OF ELECTRONIC IMAGING
卷 32, 期 4, 页码 -出版社
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.JEI.32.4.043004
关键词
generative adversarial networks; remote sensing; machine learning; deep learning; manipulation detection; deep convolutional generative adversarial network
With the increasing number of satellites, there is a rise in Earth observation imagery. This study utilizes generative adversarial networks to obtain fake images from the EuroSAT dataset and creates a dataset consisting of 14 classes and 36,000 images. By employing transfer learning models and ensemble models, the classification accuracy reaches 91.55%.
As the number of government and commercial satellites increases, there is a large increase in Earth observation (EO) imagery. Using different locations and tools, images can be taken from more than one satellite. Manipulations are carried out on these images using a variety of different methods. The number of studies that have been done on the manipulation of EO images is very small. In recent years, generative adversarial networks (GANs), a major breakthrough in deep learning, have made it very easy to obtain fake images. In this study, scene-by-scene fake images were obtained with the deep convolutional GAN on the EuroSAT dataset, which is one of the EO image sets, and fake scene images were obtained from the original scenes. In this study, a dataset called RF-EuroSAT was created. It consists of 14 classes and 36,000 images. Five transfer learning models (VGG-16, DenseNet201, MobileNetV2, RegNetY320, and ResNet152V2) were used to classify this dataset. Using these models as feature extraction and ensemble models (XGBoost, CatBoost, and LightGBM) as classifiers, the classification process was performed using our proprietary transferemble model. The best result was obtained with an accuracy of 91.55% using our transferemble model, which is developed in a modular structure. (c) 2023 SPIE and IS&T
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据