吉林大学学报（理学版）2025，Vol.63Issue(2)：492-498,7.DOI:10.13413/j.cnki.jdxblxb.2024001
基于FCA-EF模型的遥感图像变化检测方法
Remote Sensing Image Change Detection Method Based on FCA-EF Model
摘要
Abstract
Aiming at the problem of insufficient data volumes or low accuracy of labeled images in the field of remote sensing image change detection,which led to the model being unable to fully learn features,and affected the accuracy of detection,we proposed an improved FCA-EF model based on the U-Net network.Firstly,the model was based on multi-head self-attention mechanisms and Transformer module of feedforward neural networks to establish encoding layers.Through long-distance skip connection mechanism,the global features of the data were extracted in the encoding layer,achieving information transfer between different layers.Secondly,the model used convolutional neural network(CNN)module as the backbone to establish decoding layers,extracted deep local features by using the local perceptual characteristics of CNN module,and fused the global features extracted by the encoder via long-distance skip connection mechanism to enhance the model's ability to capture details and accuracy of change detection.Thirdly,a new label filling and optimization method was proposed to address the problem of incomplete information representation in label image,and its effectiveness was confirmed through ablation experiments.Finally,combined with the FCA-EF model and label filling method,the proposed method achieved excellent results inthe change detection of remote sensing images from Jilin-1 satellite.Compared with other classical models,the overall accuracy,F1 score,recall rate,intersection over union(IoU)and other indicators were improved,effectively improving the accuracy of remote sensing image change detection.关键词
遥感图像/变化检测/FCA-EF模型/标签填充方法Key words
remote sensing/change detection/FCA-EF model/label filling method分类
信息技术与安全科学引用本文复制引用
杨笑天,鱼昕,黄璐,于圣泽,刘铭..基于FCA-EF模型的遥感图像变化检测方法[J].吉林大学学报（理学版）,2025,63(2):492-498,7.基金项目
吉林省发改委基本建设项目(批准号:2022C043-2)和吉林省自然科学基金(批准号:20200201157JC). （批准号:2022C043-2）
