浏览全部资源
扫码关注微信
Published： 07 February 2021 ，
扫 描 看 全 文
王鹏，姚红雨，张弓.2021.超像元尺度下的多光谱图像超分辨率洪水淹没制图.遥感学报，25（2）： 641-652
Wang P，Yao H Y and Zhang G. 2021. Super-resolution flood inundation mapping for multispectral image based on super-pixel scale. National Remote Sensing Bulletin， 25（2）：641-652
超分辨率制图SRM（Super-resolution Mapping）技术可以有效地处理遥感图像中的混合像元，获得准确的地物类别分布信息。目前，SRM技术已经成功地应用于多光谱图像洪水淹没定位中，称为超分辨率洪水淹没制图SRFIM（Super-resolution Flood Inundation Mapping）。然而，现有的SRFIM方法往往基于像元尺度空间相关性，这种空间相关性考虑设定的矩形窗内的像元之间的空间关系，但实际情况下淹没区域与非淹没区域的形状是不规则的，因此这种像元尺度空间相关性不够准确，影响最终的洪水淹没制图精度。为了解决这一问题，提出了超像元尺度空间相关性下的多光谱图像超分辨率洪水淹没制图SSSC-SRFIM（Super-resolution Flood Inundation Mapping for Multispectral Image Based on Super-pixel Scale Spatial Correlation）。在SSSC-SRFIM中，首先利用双立方插值改善原始粗糙多光谱图像，获得改善后的图像，并利用光谱解混方法对改善后的图像进行光谱解混，获得具有每个亚像元属于淹没类别概率值的丰度图像；然后利用主成分分析法提取改善后图像的第一主成分，并利用基于多分辨率的图像分割算法分割第一主成分，获得不规则形状的超像元；再者将丰度图像与超像元进行整合计算，并引入随机游走算法计算各个超像元之间的空间相关性；最后，依据超像元空间相关性，利用基于类别单元的类别方法将淹没区域或非淹没区域标签分配给每个亚像元中，得到最终的洪水淹没制图结果。利用两个Landsat 8 OLI多光谱图像对该方法进行了评价。结果表明，与传统的SRFIM方法相比，本文提出的SSSC-SRFIM方法具有更好的效果。
Super Resolution Mapping (SRM) technology can effectively handle mixed pixels in remote sensing image and obtain the accurate distribution information of land-cover class. SRM technology is currently successfully applied to flood inundation mapping for multispectral image
which is called Super Resolution Flood Inundation Mapping (SRFIM). However
the existing SRFIM methods are often based on pixel-scale spatial correlation. This method considers the spatial relationship between pixels in the set rectangular window
but the shape of the inundation area or the non-inundation area is irregular in reality. Thus
the pixel-scale spatial correlation is insufficiently accurate
which affects the final accuracy of flood inundation mapping. Super-resolution flood inundation mapping of multispectral image based on super-pixel scale spatial correlation (SSSC-SRFIM) is proposed to solve the abovementioned problem.
In SSSC-SRFIM
the original coarse multispectral image is first improved by bicubic interpolation to obtain the improved image
and the fractional image with the proportion value of each subpixel belonging to inundation area is obtained by unmixing the improved image. The first principal component of the improved image is then extracted by principal component analysis
and the image segmentation based on multi-resolution is used to segment the first principal component to obtain the super-pixels with irregular shape. Next
the fractional image and super-pixels are integrated
and the random walk algorithm is introduced to calculate the super-pixel-scale spatial correlation. Finally
according to the super-pixel-scale spatial correlation
the label of the inundation area or the non-inundation area is assigned to each sub-pixel by the class allocation method based on the unit of object. Thus
the final result of flood inundation mapping is produced.Two Landsat 8 OLI multispectral images are used to evaluate the method. The proposed SSSC-SRFIM method has better performance than the traditional methods.In the proposed SSSC-SRFIM
the super-pixel-scale spatial correlation is more accurate than pixel-scale spatial correlation because the irregular distribution shape of the actual inundation and non-inundation areas is considered. Therefore
better flood inundation mapping result can be obtained by the proposed SSSC-SRFIM.
遥感多光谱图像洪水淹没定位超分辨率制图超像元图像分割随机游走算法
remote sensingmultispectral imageflood inundationsuper-resolution mappingsuper-pixelimage segmentationrandom walk algorithm
Atkinson P M. 2005. Sub-pixel target mapping from soft-classified, remotely sensed imagery. Photogrammetric Engineering and Remote Sensing, 71(7): 839-846 [DOI: 10.14358/PERS.71.7.839http://dx.doi.org/10.14358/PERS.71.7.839]
Chen Y H, Ge Y, Heuvelink G B M, An R and Chen Y. 2018. Object-based superresolution land-cover mapping from remotely sensed imagery. IEEE Transactions on Geoscience and Remote Sensing, 56(1): 328-340 [DOI: 10.1109/TGRS.2017.2747624http://dx.doi.org/10.1109/TGRS.2017.2747624]
Chen Y H, Ge Y, Heuvelink G B M, Hu J L and Jiang Y. 2015a. Hybrid constraints of pure and mixed pixels for soft-then-hard super-resolution mapping with multiple shifted images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5): 2040-2052 [DOI: 10.1109/JSTARS.2015.2417191http://dx.doi.org/10.1109/JSTARS.2015.2417191]
Chen Y H, Ge Y and Song D J. 2015b. Superresolution land-cover mapping based on high-accuracy surface modeling. IEEE Geoscience and Remote Sensing Letters, 12(12): 2516-2520 [DOI: 10.1109/lgrs.2015.2489683http://dx.doi.org/10.1109/lgrs.2015.2489683]
Drăgut L, Tiede D and Levick S R. 2010. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. International Journal of Geographical Information Science, 24(6): 859-871 [DOI: 10.1080/13658810903174803http://dx.doi.org/10.1080/13658810903174803]
Ge Y, Chen Y H, Stein A, Li S P and Hu J L. 2016. Enhanced subpixel mapping with spatial distribution patterns of geographical objects. IEEE Transactions on Geoscience and Remote Sensing, 54(4): 2356-2370 [DOI: 10.1109/TGRS.2015.2499790http://dx.doi.org/10.1109/TGRS.2015.2499790]
Ji T K and Zhao Z M. 2005. The theory to evaluate the image spatial resolution quantitatively. Journal of Remote Sensing, 9(4): 486-493
季统凯, 赵忠明. 2005. 海啸地区遥感图像空间分辨率定量评价研究. 遥感学报, 9(4): 486-493 [DOI: 10.3321/j.issn:1007-4619.2005.04.022http://dx.doi.org/10.3321/j.issn:1007-4619.2005.04.022]
Jin H R, Mountrakis G and Li P J. 2012. A super-resolution mapping method using local indicator variograms. International Journal of Remote Sensing, 33(24): 7747-7773 [DOI: 10.1080/01431161.2012.702234http://dx.doi.org/10.1080/01431161.2012.702234]
Kang X D, Li S T, Fang L Y, Li M X and Benediktsson J A. 2015. Extended random walker-based classification of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 53(1): 144-153 [DOI: 10.1109/TGRS.2014.2319373http://dx.doi.org/10.1109/TGRS.2014.2319373]
Li L Y, Chen Y, Xu T B, Liu R, Shi K F and Huang C. 2015a. Super-resolution mapping of wetland inundation from remote sensing imagery based on integration of back-propagation neural network and genetic algorithm. Remote Sensing of Environment, 164: 142-154 [DOI: 10.1016/j.rse.2015.04.009http://dx.doi.org/10.1016/j.rse.2015.04.009]
Li L Y, Chen Y, Xu T B, Meng L K, Huang C and Shi K F. 2020. Spatial attraction models coupled with Elman neural networks for enhancing sub-pixel urban inundation mapping. Remote Sensing, 12(13): 2068 [DOI: 10.3390/rs12132068http://dx.doi.org/10.3390/rs12132068]
Li L Y, Chen Y, Xu T B, Shi K F, Huang C, Liu R, Lu B B and Meng L K. 2019. Enhanced super-resolution mapping of urban floods based on the fusion of support vector machine and general regression neural network. IEEE Geoscience and Remote Sensing Letters, 16(8): 1269-1273 [DOI: 10.1109/LGRS.2019.2894350http://dx.doi.org/10.1109/LGRS.2019.2894350]
Li L Y, Chen Y, Yu X, Liu R and Huang C. 2015b. Sub-pixel flood inundation mapping from multispectral remotely sensed images based on discrete particle swarm optimization. ISPRS Journal of Photogrammetry and Remote Sensing, 101: 10-21 [DOI: 10.1016/j.isprsjprs.2014.11.006http://dx.doi.org/10.1016/j.isprsjprs.2014.11.006]
Li L Y, Xu T B and Chen Y. 2016. Improved urban flooding mapping from remote sensing images using generalized regression neural network-based super-resolution algorithm. Remote Sensing, 8(8): 625 [DOI: 10.3390/rs8080625http://dx.doi.org/10.3390/rs8080625]
Li X D, Du Y, Ling F, Feng Q and Fu B T. 2014. Superresolution mapping of remotely sensed image based on Hopfield neural network with anisotropic spatial dependence model. IEEE Geoscience and Remote Sensing Letters, 11(7): 1265-1269 [DOI: 10.1109/LGRS.2013.2291778http://dx.doi.org/10.1109/LGRS.2013.2291778]
Ling F, Du Y, Zhang Y H, Li X D and Xiao F. 2015. Burned-area mapping at the subpixel scale with MODIS images. IEEE Geoscience and Remote Sensing Letters, 12(9): 1963-1967 [DOI: 10.1109/LGRS.2015.2441135http://dx.doi.org/10.1109/LGRS.2015.2441135]
Ling F and Foody G M. 2019. Super-resolution land cover mapping by deep learning. Remote Sensing Letters, 10(6): 598-606 [DOI: 10.1080/2150704X.2019.1587196http://dx.doi.org/10.1080/2150704X.2019.1587196]
Ling F, Li W B, Du Y and Li X D. 2011. Land cover change mapping at the subpixel scale with different spatial-resolution remotely sensed imagery. IEEE Geoscience and Remote Sensing Letters, 8(1): 182-186 [DOI: 10.1109/LGRS.2010.2055034http://dx.doi.org/10.1109/LGRS.2010.2055034]
Ling F, Li X D, Xiao F, Fang S M and Du Y. 2012. Object-based sub-pixel mapping of buildings incorporating the prior shape information from remotely sensed imagery. International Journal of Applied Earth Observation and Geoinformation, 18: 283-292 [DOI: 10.1016/j.jag.2012.02.008http://dx.doi.org/10.1016/j.jag.2012.02.008]
Ling F, Wu S J, Xiao F, Wu K and Li X D. 2011. Sub-pixel mapping of remotely sensed imagery: a review. Journal of Image and Graphics, 16(8): 1335-1345
凌峰, 吴胜军, 肖飞, 吴柯, 李晓冬. 2011. 遥感影像亚像元定位研究综述. 中国图象图形学报, 16(8): 1335-1345 [DOI: 10.11834/jig.20110815http://dx.doi.org/10.11834/jig.20110815]
Ma A L, Zhong Y F, He D and Zhang L P. 2018. Multiobjective subpixel land-cover mapping. IEEE Transactions on Geoscience and Remote Sensing, 56(1): 422-435 [DOI: 10.1109/TGRS.2017.274 8701http://dx.doi.org/10.1109/TGRS.2017.2748701]
Makido Y, Shortridge A and Messina J P. 2007. Assessing alternatives for modeling the spatial distribution of multiple land-cover classes at sub-pixel scales. Photogrammetric Engineering and Remote Sensing, 73(8): 935-943 [DOI: 10.14358/PERS.73.8.935http://dx.doi.org/10.14358/PERS.73.8.935]
Olthof I and Tolszczuk-Leclerc S. 2018. Comparing Landsat and RADARSAT for current and historical dynamic flood Mapping. Remote Sensing, 10(5): 780 [DOI: 10.3390/rs10050780http://dx.doi.org/10.3390/rs10050780]
Verhoeye J and De Wulf R. 2002. Land cover mapping at sub-pixel scales using linear optimization techniques. Remote Sensing of Environment, 79(1): 96-104 [DOI: 10.1016/S0034-4257(01)00242-5http://dx.doi.org/10.1016/S0034-4257(01)00242-5]
Villa A, Chanussot J, Benediktsson J A and Jutten C. 2011. Spectral unmixing for the classification of hyperspectral images at a finer spatial resolution. IEEE Journal of Selected Topics in Signal Processing, 5(3): 521-533 [DOI: 10.1109/JSTSP.2010.2096798http://dx.doi.org/10.1109/JSTSP.2010.2096798]
Wang L G, Liu D F, Wang Q M and Wang Y. 2013. Spectral unmixing model based on least squares support vector machine with unmixing residue constraints. IEEE Geoscience and Remote Sensing Letters, 10(6): 1592-1596 [DOI: 10.1109/LGRS.2013.2262371http://dx.doi.org/10.1109/LGRS.2013.2262371]
Wang P, Wang L G and Chanussot J. 2016. Soft-then-hard subpixel land cover mapping based on spatial-spectral interpolation. IEEE Geoscience and Remote Sensing Letters, 13(12): 1851-1854 [DOI: 10.1109/LGRS.2016.2614810http://dx.doi.org/10.1109/LGRS.2016.2614810]
Wang P, Wang L G, Leung H and Zhang G. 2019. Subpixel mapping based on hopfield neural network with more prior information. IEEE Geoscience and Remote Sensing Letters, 16(8): 1284-1288 [DOI: 10.1109/LGRS.2019.2895629http://dx.doi.org/10.1109/LGRS.2019.2895629]
Wang P, Wang L G, Mura M D and Chanussot J. 2017. Using multiple subpixel shifted images with spatial-spectral information in soft-then-hard subpixel mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(6): 2950-2959 [DOI: 10.1109/JSTARS.2017.2713439http://dx.doi.org/10.1109/JSTARS.2017.2713439]
Wang Q M, Atkinson P M and Shi W Z. 2015. Fast subpixel mapping algorithms for subpixel resolution change detection. IEEE Transactions on Geoscience and Remote Sensing, 53(4): 1692-1706 [DOI: 10.1109/TGRS.2014.2346535http://dx.doi.org/10.1109/TGRS.2014.2346535]
Wang Q M, Shi W Z and Atkinson P M. 2014b. Sub-pixel mapping of remote sensing images based on radial basis function interpolation. SPRS Journal of Photogrammetry and Remote Sensing, 92: 1-15 [DOI: 10.1016/j.isprsjprs.2014.02.012http://dx.doi.org/10.1016/j.isprsjprs.2014.02.012]
Wang Q M, Shi W Z and Wang L G. 2014a. Allocating classes for soft-then-hard subpixel mapping algorithms in units of class. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2940-2959 [DOI: 10.1109/TGRS.2013.2267802http://dx.doi.org/10.1109/TGRS.2013.2267802]
Wang Q M, Wang L G and Liu D F. 2012. Particle swarm optimization-based sub-pixel mapping for remote-sensing imagery. International Journal of Remote Sensing, 33(20): 6480-6496 [DOI: 10.1080/01431161.2012.690541http://dx.doi.org/10.1080/01431161.2012.690541]
Xie H, Luo X, Xu X, Pan H Y and Tong X H. 2016. Automated subpixel surface water mapping from heterogeneous urban environments using Landsat 8 OLI Imagery. Remote Sensing, 8(7): 584 [DOI: 10.3390/rs8070584http://dx.doi.org/10.3390/rs8070584]
Xu X, Zhong Y F, Zhang L P and Li P X. 2011. A sub-pixel mapping algorithm based on BP neural network with spatial autocorrelation function for remote sensing imagery. Acta Geodaetica et Cartographica Sinica, 40(3): 307-311
许雄, 钟燕飞, 张良培, 李平湘. 2011. 基于空间自相关BP神经网络的遥感影像亚像元定位. 测绘学报, 40(3): 307-311
Xu X, Zhong Y F, Zhang L P and Zhang H Y. 2013. Sub-pixel mapping based on a MAP model with multiple shifted hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(2): 580-593 [DOI: 10.1109/JSTARS. 2012.2227246http://dx.doi.org/10.1109/JSTARS.2012.2227246]
Zhang Y H, Ling F, Li X D and Du Y. 2015. Super-resolution land cover mapping using multiscale self-similarity redundancy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(11): 5130-5145 [DOI: 10.1109/JSTARS.2015.24 80120http://dx.doi.org/10.1109/JSTARS.2015.2480120]
相关文章
相关作者
相关机构
京公网安备11010802024621