基于混合注意力的遥感图像超分辨率重建

打开文本图片集

中图分类号：TP391 文献标志码：A 文章编号：1672-1098（2025）01-0064-10

Abstract：Objective To solve theproblems of local ambiguity inthe remote sensing images and lossof some detail informationinthe reconstruction.Methods A super-resolution reconstruction algorithm for remote sensing images based on dilated convolution and mixed atention was proposed.Firstly，the shallow feature map was obtained through the shallow feature extraction module，and then the convolution，dilated convolution and nonlinear activation block were combined to expandtheoverallreceptive fieldand improve thestabilityof the training proces，oasto enhance theability to express deep features.Secondly，the cascaded spatialatentionandchannel attention modules wereused to solve theproblemof high-frequency information lossFinally，the extracted features were upsampled and reconstructed to obtain high-resolution images.Results On the NWPU RESISC45and UCMerced-LandUse datasets，the simulationresults showed thatthe peak signal-to-noise ratio andthe structural similarity of the proposed algorithm were better than those of the compared algorithms，and the reconstructed images highlighted the texture details better in the subjective visual efect.Conclusion The proposed algorithm has better reconstruc tion effect and improves the quality and usability of remote sensing images.

Key Words：super-resolution reconstruction；remote sensing images；dilated convolution；attention mechanisms；Deep learning

遥感技术的不断进步为地球观测提供了丰富的遥感图像，近年来遥感图像作为重要数据在环境监测[1]、城市规划、军事侦察[2]、能源勘探等领域发挥着重要作用。（剩余12306字）