基于FCA-EF模型的遥感图像变化检测方法  

Remote Sensing Image Change Detection MethodBased on FCA-EF Model

作　　者：杨笑天 鱼昕 黄璐 于圣泽 刘铭 YANG Xiaotian;YU Xin;HUANG Lu;YU Shengze;LIU Ming(Shaanxi Academy of Aerospace Technology Application Company Limited,Xi’an 710100,China;China Academy of S pace Technology(Xi’an),Xi’an 710100,China;School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]陕西航天技术应用研究院有限公司,西安710100 [2]西安空间无线电技术研究所,西安710100 [3]长春工业大学数学与统计学院,长春130012

出　　处：《吉林大学学报(理学版)》2025年第2期492-498,共7页Journal of Jilin University:Science Edition

基　　金：吉林省发改委基本建设项目(批准号:2022C043-2);吉林省自然科学基金(批准号:20200201157JC)。

摘　　要：针对在遥感图像变化检测中数据量不足或标签图像精确度较低时,导致模型无法充分学习特征,影响检测精确度的问题,提出一个基于U-Net网络改进后的FCA-EF模型.该模型首先基于多头自注意力机制和前馈神经网络的Transformer模块建立编码层,通过长距离跳跃连接机制在编码层对数据全局特征进行提取,实现了不同层级之间的信息传递.其次,该模型以卷积神经网络(CNN)模块为骨干建立解码层,利用CNN模块的局部感知特性提取深层次局部特征,并通过长距离跳跃连接机制融合编码器所提取的全局特征,增强模型对细节的捕捉能力与变化检测的准确性.再次,针对标签图像表示信息不完整的问题提出一种新的标签填充与优化方法,并经过消融实验证明了其有效性.最后,结合FCA-EF模型与标签填充方法,在吉林一号卫星遥感图像的变化检测中取得了优异结果,在总体精确度、F_1得分、召回率、交并比等指标上与其他经典模型相比均有提升,有效提高了遥感图像变化检测的精确度.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,F 1 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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]