一种多光谱遥感影像与航拍影像融合算法

详细信息    查看全文 | 推荐本文 |

英文篇名：A Fusion Algorithm of Multispectral Remote Sensing Image and Aerial Image 作者：李小军 ; 闫浩文 ; 杨树文 ; 牛丽峰 英文作者：LI Xiaojun;YAN Haowen;YANG Shuwen;NIU Lifeng;Faculty of Geomatics,Lanzhou Jiaotong University;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring; 关键词：遥感图像融合 ; 无人机航拍影像 ; 脉冲耦合神经网络 ; 多光谱影像 ; 图像分割 英文关键词：remote sensing image fusion;;UAV aerial image;;pulse-coupled neural network;;multispectral image;;image segmentation 中文刊名：遥感信息 英文刊名：Remote Sensing Information 机构：兰州交通大学测绘与地理信息学院;甘肃省地理国情监测工程实验室; 出版日期：2019-08-20 出版单位：遥感信息 年：2019 期：04 基金：国家重点研发计划重点专项(2017YFB0504201);国家重点研发计划重点专项(2017YFB0504203);; 国家自然科学基金(41861055、41761082);; 兰州交通大学优秀平台支持(201806) 语种：中文; 页：14-18 页数：5 CN：11-5443/P ISSN：1000-3177 分类号：P237;TP751

摘要

无人机航拍影像空间分辨率高,纹理信息丰富,但其光谱信息匮乏,不利于遥感信息解译。为此提出一种基于脉冲耦合神经网络模型的融合算法,通过计算非规则区域的统计特性,将无人机航拍影像的亚米级高空间分辨率信息注入到遥感卫星多光谱影像中,以获取具有亚米级空间分辨率和高的光谱分辨率的遥感融合影像。通过定性和定量的对比实验,表明该算法优于经典的遥感影像融合方法,同时验证了其在减小光谱扭曲和空间纹理细节保持等方面的有效性。
        Aerial images captured by UAV have high spatial resolution and rich texture.However,the lack of spectral information makes it difficult to use for image interpretation.Therefore,a novel pulse-coupled neural network based fusion algorithm is proposed.Both the sub-meter spatial resolution and high spectral resolution can be obtained by injecting the information of sub-meter spatial resolution of UAV to the multispectral image of the remote sensing satellite,which is achieved by performing the statistics in irregular regions of the remote sensing images.The qualitative and quantitative experiments demonstrate that the proposed method outperforms the traditional remote sensing fusion methods.The validity of the fusion algorithm in reducing spectral distortion and preserving spatial texture details is also verified by comparative experiments.

引文

[1]万刚.无人机测绘技术及应用[M].北京:测绘出版社,2015.
    [2]MALLAT S G.A theory for multiresolution signal decomposition:the wavelet representation[M].Washington DC:IEEE Computer Society,1989.
    [3]NASON G P,SILVERMAN B W.The stationary wavelet transform and some statistical applications[J].Science,1995,346(6212):918-919.
    [4]VIVONE G,RESTAINO R,MURA M D,et al.Contrast and error-based fusion schemes for multispectral image pansharpening[J].IEEE Geoscience&Remote Sensing Letters,2013,11(5):930-934.
    [5]肖新耀,许宁,尤红建.一种基于àtrous小波和联合稀疏表示的遥感图像融合方法[J].遥感技术与应用,2015,30(5):1021-1026.
    [6]BURT P J,ADELSON E H.The laplacian pyramid as a compact image code[J].IEEE Transactions on Communications,2003,31(4):532-540.
    [7]殷明,庞纪勇,魏远远,等.结合NSDTCT和稀疏表示的遥感图像融合[J].光子学报,2016,45(1):10-17.
    [8]吴一全,陶飞翔.改进投影梯度NMF的NSST域多光谱与全色图像融合[J].光学学报,2015,35(4):129-138.
    [9]JOHNSON J L,PADGETT M L.PCNN models and applications[J].IEEE Transactions on Neural Networks,1999,10(3):480-498.
    [10]MA Y,ZHAN K,WANG Z.Applications of pulse-coupled neural networks[M].Beijing:Higher Education Press,2010.
    [11]VIVONE G,ALPARONE L,CHANUSSOT J,et al.A critical comparison among pansharpening algorithms[J].IEEETransactions on Geoscience&Remote Sensing,2015,53(5):2565-2586.
    [12]RESTAINO R,VIVONE G,DALLA M M,et al.Fusion of multispectral and panchromatic images based on morphological operators[J].IEEE Transactions on Image Processing,2016,25(6):2882-2895.
    [13]LABEN C A,BROWER B V.Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening:US,US6011875[P].2000.
    [14]TU T M,SU S C,SHYU H C,et al.A new look at IHS-like image fusion methods[J].Information Fusion,2001,2(3):177-186.
    [15]PSJR C,SIDES S C,ANDERSON J A.Comparison of three different methods to merge multiresolution and multispectral data:Landsat TM and SPOT panchromatic[J].Photogrammetric Engineering&Remote Sensing,1991,57(3):265-303.