空间控制技术与应用2023，Vol.49Issue(6)：77-85,9.DOI:10.3969/j.issn.1674-1579.2023.06.008
基于深度学习网络的遥感图像异常检测方法研究
An Anomaly Detection Method for Remote Sensing Image Based on Deep Learning Network
摘要
Abstract
A high-performance anomaly detection model has been constructed to address the problem of sparse a-nomalous image data in the real world.A two-stage framework anomaly detection model is built using only normal training data and a small amount of synthetic anomaly sample.First,a ResNet-18 encoder model is trained to ex-tract representation by the pretext of classifying normal data and synthetic anomaly data.Then,a single classifier for anomaly images is built through modelling the distribution of normal data representations using Gaussian density estimation.GradCAM is applied to extend the model,enabling the anomaly detection model to locate anomaly re-gions without labels.Finally,experiments are conducted on a simulated anomaly detection dataset using real-world images,demonstrating that the proposed algorithm can detect anomaly and provide location results in remote sensing images that are even difficult to recognize with human eyes.关键词
异常检测/遥感图像/深度学习/卷积神经网络Key words
anomaly detection/remote sensing/deep learning/convolutional neural network分类
信息技术与安全科学引用本文复制引用
曹哲骁,傅瑶,王丽,苏盈,郭云翔,王田..基于深度学习网络的遥感图像异常检测方法研究[J].空间控制技术与应用,2023,49(6):77-85,9.基金项目
国家自然科学基金资助项目(61972016和62032016)和北京市科技新星资助项目(20220484106和202304844451)Supported by National Natural Science Foundation of China(61972016 and 62032016)and Beijing Nova Program(20220484106 and 20230484451) （61972016和62032016）
