郭岑,尹增山,高爽

• 1:中国科学院上海微系统与信息技术研究所
• 2:中国科学院微小卫星创新研究院
• 3:中国科学院大学

摘要(Abstract)：

为了提升遥感图像超分辨率重建算法纹理细节信息还原能力,该文提出了一种基于特征空间感知损失深度残差网络的遥感图像超分辨率重建算法。该算法增加了深度残差网络中的残差块数量,在网络末端采用了亚像素卷积的方法,并在损失函数中增加了特征空间感知损失。在UCMerced_LandUse数据集上进行了训练,并在UCMerced_LandUse数据集和Draper Satellite Image Chronology数据集上进行了测试。测试结果证实了该算法与其他算法相比在峰值信噪比和结构相似性指数上均有一定的提高,证实了该算法较好的超分辨率重建效果与还原遥感图像纹理细节信息的能力。

关键词(KeyWords)： 超分辨率重建;遥感图像;深度残差网络;亚像素卷积;特征空间感知损失

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目(2016YFB0501100)

作者(Author): 郭岑,尹增山,高爽

DOI: 10.16251/j.cnki.1009-2307.2020.05.008

参考文献(References)：

• [1] 胡龙珍.遥感卫星图像和视频的超分辨率重建技术研究[D].上海:中科院上海微系统与信息技术研究所,2018.(HU Longzhen.Research on super-resolution reconstruction technology of remote sensing images and satellite video[D].Shanghai:Shanghai Institute of Microsystem and Information Technology,2018.)
• [2] 胡龙珍,尹增山,高爽.基于 MAP-EM的多帧遥感影像超分辨率技术研究[J].电子设计工程,2018,26(21):180-184.(HU Longzhen,YIN Zengshan,GAO Shuang.Super resolution reconstruction of multi-frame remote sensing images based on MAP-EM[J].Electronic Design Engineering,2018,26(21):180-184.)
• [3] 韩森森.深度学习在超分辨率图像重建中的应用[J].计算机时代,2017(7):38-41.(HAN Sensen.Application of deep learning in super-resolution image reconstruction[J].Computer Era,2017(7):38-41.)
• [4] BABACAN S D,MOLINA R,KATSAGGELOS A K.Variational Bayesian super resolution[J].IEEE Transactions on Image Processing,2011,20(4):984-999.
• [5] LIU C,SUN D Q.On Bayesian adaptive video super resolution[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2014,36(2):346-360.
• [6] BELEKOS S P,GALATSANOS N P,KATSAGGELOS A K.Maximum a posteriori video super-resolution using a new multichannel image prior[J].IEEE Trans on Image Processing,2010,19(6):1451-1464.
• [7] GLASNER D,BAGON S,IRANI M.Super-resolution from a single image[C]//IEEE International Conference on Computer Vision.Kyoto,Japan:IEEE,2009:349-356.
• [8] YANG C Y,HUANG J B,YANG M H.Exploiting self-similarities for single frame super-resolution[C]//Asian Conference on Computer Vision.New Zealand:Springer,2010:497-510.
• [9] YANG J C,WRIGHT J,Huang T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
• [10] WALHA R,DRIRA F,LEBOURGEOIS F,et al.Sparse coding with a coupled dictionary learning approach for textual image super-resolution[C]//International Conference on Pattern Recognition.Stockholm,Sweden:IEEE,2014:4459-4464.
• [11] FREEDMAN G,FATTAL R.Image and video upscaling from local self-examples[J].ACM Transactions on Graphics,2011,30(2):12.
• [12] GAO X,ZHANG K,TAO D,et al.Joint learning for single-image super-resolution via a coupled constraint[J].IEEE Transactions on Image Processing,2012,21(2):469-480.
• [13] YEGANLI F,OZKARAMANLI H.Improved online dictionary learning for sparse signal representation[C]//Signal Processing and Communications Applications Conference.Trabzon,Turkey:IEEE,2014:1702-1705.
• [14] DONG C,CHEN C L,HE K,et al.Image super-resolution using deep convolutional network[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,38(2):295-307.
• [15] WANG Z W,LIU D,YANG J C,et al.Deep networks for image super-resolution with sparse prior[C]//IEEE International Conference on Computer Vision.Santiago,Chile:IEEE,2015:370-378.
• [16] KIM J,LEE J K,LEE K M.Deeply-recursive convolutional network for image super-resolution[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA:IEEE,2016:1646-1654.
• [17] SHI W,CABALLERO J,HUSZAR F,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,HI,USA:IEEE,2017:2848-2857.
• [18] LEDIG C,THEIS L,HUSZAR F,et al.Photo-realistic single image super-resolution using a generative adversarial network[C]//IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,HI,USA:IEEE,2017:105-114.
• [19] ZHAO H,GALLO O,FROSIO I,et al.Loss functions for image restoration with neural networks[J].IEEE Transactions on Computational Imaging,2017,3(1):47-57.
• [20] DOSOVITSKIY A,BROX T.Generating images with perceptual similarity metrics based on deep networks[C]//Neural Information Processing Systems.New York:Curran Associates,2016:658-666.