郝明达;普运伟;周家厚;杨洋;陈如俊;

• 1:昆明理工大学国土资源工程学院
• 2:昆明理工大学计算中心

摘要(Abstract)：

为从航空RGB遥感影像中预测高光谱影像中有用的地物属性信息，提高航空RGB遥感影像光谱的分辨率，提出一种轻量型的深度学习网络模型。所提模型组合了密集卷积神经网络架构和自适应注意力机制的优点，构建了一种新型密集注意力卷积神经网络模型(dense attention convolutional neural network model, DACNN model)。在真实的多模态AeroRIT场景影像和同源的雄安航空遥感影像上的多种定量对比实验结果表明，所提出的网络架构可以生成与原始高光谱遥感影像相似的空间特征和光谱特征，并且所需参数量显著降低，具有较好的性能和适用性，且所提模型架构方法具有一定的通用性。

关键词(KeyWords)： 高光谱遥感重建;光谱超分辨率;深度学习;自适应注意力机制;密集卷积神经网络

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 郝明达;普运伟;周家厚;杨洋;陈如俊;

参考文献(References)：

• [1] 桂德竹，张成成，洪志刚.我国航空遥感发展现状及若干建议[J].遥感信息，2013,28(1):119-122,48.
• [2] GALLIANI S,LANARAS C,MARMANIS D,et al.Learned spectral super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA:IEEE,2017:372.
• [3] ARAD B,BEN-SHAHAR O,TIMOFTE R,et al.NTIRE 2018 challenge on spectral reconstruction from RGB images[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Salt Lake City,UT,USA:IEEE,2018:18-22.
• [4] ARAD B,TIMOFTE R,BEN-SHAHAR O,et al.NTIRE 2020 challenge on spectral reconstruction from an RGB image[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Seattle,WA,USA:IEEE,2020:1806-1822.
• [5] 施展.基于深度学习的高光谱图像空谱超分辨率重建[D].合肥：中国科学技术大学，2020.
• [6] ZHAO Y,PO L M,YAN Q,et al.Hierarchical regression network for spectral reconstruction from RGB images[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Seattle,WA,USA:IEEE,2020:422-423.
• [7] HUANG G,LIU Z,LAURENS V,et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA:IEEE,2017:4700-4708.
• [8] LI J,WU C,SONG R,et al.Adaptive weighted attention network with camera spectral sensitivity prior for spectral reconstruction from RGB images[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Seattle,WA,USA:IEEE,2020:1894-1903.
• [9] HE J,LI J,YUAN Q,et al.Spectral response function-guided deep optimization-driven network for spectral super-resolution[J].IEEE transactions on neural networks and learning systems,2022,33(9):4213-4227.
• [10] DENG L,SUN J,CHEN Y,et al.M2H-Net:a reconstruction method for hyperspectral remotely sensed imagery[J].ISPRS journal of photogrammetry and remote sensing,2021,173(2):323-348.
• [11] RANGNEKAR A,MOKASHI N,IENTILUCCI E J,et al.AeroRIT:a new scene for hyperspectral image analysis[J].IEEE transactions on geoscience and remote sensing,2020,58(11):8116-8124.
• [12] GEWALI U B,MONTEIRO S T,SABER E.Spectral super-resolution with optimized bands[J].Remote sensing,2019,11(14):1648.
• [13] WANG Y,YANG Y,BAI J,et al.Evolving attention with residual convolutions[C]//Proceedings of International Conference on Machine Learning.[S.l.]:PMLR,2021:10971-10980.
• [14] MOU C,ZHANG J,FAN X,et al.COLA-Net:collaborative attention network for image restoration[J].IEEE transactions on multimedia,2021,24:1366-1377.
• [15] WANG X,GIRSHICK R,GUPTA A,et al.Non-local neural networks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:7794-7803.