基于多尺度注意力特征与孪生判别的遥感影像变化检测及其抗噪性研究  

Change Detection of Remote Sensing Image Based on Siamese Multi-scale Attention Network and Its Anti-noise Ability Research

作　　者：杜俊翰 赖健 王雪[1,2] 谭琨 DU Junhan;LAI Jian;WANG Xue;TAN Kun(School of Geographic Science,East China Normal University,Shanghai 200241,China;Key Laboratory of Geographic Information Science(Ministry of Education),East China Normal University,Shanghai 200241,China;Shanghai High Resolution to the Earth Observation System of Data and Application Center,Shanghai 200240,China)

机构地区：[1]华东师范大学地理科学学院,上海200241 [2]华东师范大学地理信息科学教育部重点实验室,上海200241 [3]高分辨率对地观测系统上海数据与应用中心,上海200240

出　　处：《数据采集与处理》2022年第1期35-48,共14页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金面上项目(41871337,42171335)。

摘　　要：遥感影像在实际土地监测中其检测精度会受到影像数据中噪声的影响。为了提升变化检测方法的精度,本文提出了一种结合多尺度特征提取和注意力机制的孪生卷积神经网络的变化检测方法。首先使用含有不同膨胀率的空洞卷积和空间注意力模块组成多尺度特征提取模块;然后将同一卷积层的特征图相减获取前后两时期影像的差异特征图,并使用通道注意力机制增强特征提取效果;最后通过全连接层输出变化检测结果。将本文方法与目前已有的一些变化检测方法在未添加噪声的原始遥感影像数据和添加噪声后的遥感影像数据上进行对比分析。结果表明:(1)支持向量机这类采用单个像素光谱信息作为输入的方法受图像中噪声影响较大,以卷积神经网络为基础的方法受噪声影响较小;(2)本文提出的变化检测方法与其他方法相比检测精度较高且受噪声影响较小,获得了较好的变化检测结果。Remote sensing image change detection has resulted in great breakthroughs in the field of land cover observations.However,the noise of remote sensing image will impact the performance of the change detection methods.To improve the accuracy of change detection,a change detection method based on the Siamese multi-scale attention network(SMA-Net)has been proposed.Firstly,we combine atrous convolutional layers with different dilated rates and spatial attention module to get the multi-scale feature extraction module.Then,the feature maps on the same layer are subtracted to get the difference feature maps and the channel attention mechanism is used to enhance the feature extraction effect.Finally,the change detection result is output by fully connection layers.The proposed method is compared with other change detection methods on the original remote sensing image data with or without noise data.The experimental result shows that the change detection method which uses the spectral information of a single pixel as input,like support vector machine method,is susceptible to the image noise,and the convolutional neural network(CNN)based method is much less susceptible to the image noise.The proposed SMA-Net outperforms other methods on the accuracy and is less susceptible to the image noise.

关 键 词：遥感影像 变化检测 深度学习 图像噪声 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]