高仁强,陈亮雄,杨静学,秦雁

• 1:广东省水利水电科学研究院河口水利技术国家地方联合工程实验室

摘要(Abstract)：

针对现有对象级变化检测方法在高分辨率影像上受影像配准误差的影响而表现不佳的现状,提出了一种顾及像元邻域的遥感影像随机森林变化检测新方法。该方法首先在像元尺度上提取前后两时相的光谱特征图和LBP纹理特征图,在此基础上考虑像元邻域关系计算对应的差分特征图;接着采用多尺度分割技术对两时相的叠合影像进行分割;最后利用随机森林算法模型实现变化检测,并以鹤地水库2014和2018年两期Spot卫星影像为数据源验证方法的有效性。结果表明:(1)综合考虑对象的同质性指数HI和对象的异质性指数MI的综合评价函数F能为最优分割尺度的选择提供客观依据;(2)考虑像元邻域建立匹配关系可以削弱由于不同时相影像间的配准误差所引起的像元误匹配风险,变化检测的精度随着邻域窗口的增大呈现出先升后降的特征;(3)本文方法的变化检测精度约为95%,优于现有的面向对象的变化矢量分析检测方法。

关键词(KeyWords)： 高分辨率遥感;面向对象;变化检测;随机森林;鹤地水库

Abstract:

Keywords:

基金项目(Foundation): 广东省水利科技创新项目(2017-15);; 广东省自然科学基金项目(2017A030313238)

作者(Author): 高仁强,陈亮雄,杨静学,秦雁

DOI: 10.16251/j.cnki.1009-2307.2020.11.019

参考文献(References)：

• [1] 袁敏,肖鹏峰,冯学智,等.基于协同分割的高分辨率遥感图像变化检测[J].南京大学学报(自然科学),2015,51(5):1039-1048.(YUAN Min,XIAO Pengfeng,FENG Xuezhi,et al.Change detection from high-resolution remotely sensed images based on cosegmentation[J].Journal of Nanjing University(Natural Sciences),2015,51(5):1039-1048.)
• [2] 张良培,武辰.多时相遥感影像变化检测的现状与展望[J].测绘学报,2017,46(10):1447-1459.(ZHANG Liangpei,WU Chen.Advance and future development of change detection for multi-temporal remote sensing imagery[J].Acta Geodaetica et Cartographica Sinica,2017,46(10):1447-1459.)
• [3] 冯文卿,眭海刚,涂继辉,等.高分辨率遥感影像的随机森林变化检测方法[J].测绘学报,2017,46(11):1880-1890.(FENG Wenqing,SUI Haigang,TU Jihui,et al.Change detection method for high resolution remote sensing images using random forest[J].Acta Geodaetica et Cartographica Sinica,2017,46(11):1880-1890.)
• [4] HUSSAIN M,CHEN D,CHENG A,et al.Change detection from remotely sensed images:from pixel-based to object-based approaches[J].ISPRS Journal of Photogrammetry and Remote Sensing,2013,80:91-106.
• [5] GAMANYA R,MAEYER P D,DAPPER M D.Object-oriented change detection for the city of harare,zimbabwe[J].Expert Systems with Applications,2009,36(1):571-588.
• [6] DOXANI G,KARANTZALOS K,STRATI M T.Monitoring urban changes based on scale-space filtering and object-oriented classification[J].International Journal of Applied Earth Observation and Geoinformation,2012,15:38-48.
• [7] WESSELS J K,Van den BERGH F,ROY P D,et al.Rapid land cover map updates using change detection and robust random forest classifiers[J].Remote Sensing,2016,8(11):888.
• [8] KAIMIN S,YAN C.The application of objects change vector analysis in object-level change detection:proceedings of the international conferenceon computational intelligence and industrial application(PACIIA)[Z].Wuhan:[s.n.],2010.
• [9] LIANG L,XUE L,YUN Z,et al.Change detection for high-resolution remote sensing imagery using object-oriented change vector analysis method[Z].Geoscience & Remote Sensing Symposium,2016.
• [10] 李亮,舒宁,王凯,等.融合多特征的遥感影像变化检测方法[J].测绘学报,2014,43(9):945-953.(LI Liang,SHU Ning,WANG Kai,et al.Change detection experimental study based on spectral and texture features[J].Acta Geodaetica et Cartographica Sinica,2014,43(9):945-953.)
• [11] 王琰,舒宁,龚龑.高分辨率遥感影像土地利用变化检测方法研究[J].国土资源遥感,2012,24(1):43-47.(WANG Yan,SHU Ning,GONG Yan.A study of land use change detection based on high resolution remote sensing images[J].Remote Sensing for Land & Resources,2012,24(1):43-47.)
• [12] ZHANG X,XIAO P,FENG X,et al.Separate segmentation of multi-temporal high-resolution remote sensing images for object-based change detection in urban area[J].Remote Sensing of Environment,2017,201:243-255.
• [13] CHEN Q,CHEN Y.Multi-feature object-based change detection using self-adaptive weight change vector analysis[J].Remote Sensing,2016,8(7):549.
• [14] 赵敏,赵银娣.面向对象的多特征分级CVA遥感影像变化检测[J].遥感学报,2018,22(1):119-131.(ZHAO Min,ZHAO Yindi.Object-oriented and multi-feature hierarchical change detection based on CVA for high-resolution remote sensing imagery[J].Journal of Remote Sensing,2018,22(1):119-131.)
• [15] 李春干,梁文海.基于面向对象变化向量分析法的遥感影像森林变化检测[J].国土资源遥感,2017,29(3):77-84.(LI Chungan,LIANG Wenhai.Forest change detection using remote sensing image based on object-oriented change vector analysis[J].Remote Sensing for Land & Resources,2017,29(3):77-84.)
• [16] 赖继文,唐健林.面向对象的遥感影像变化检测方法[J].测绘科学,2017,42(8):111-115.(LAI Jiwen,TANG Jianlin.Object-based change detection method of remote sensing images[J].Science of Surveying and Mapping,2017,42(08):111-115.)
• [17] FENG W,SUI H,TU J,et al.A novel change detection approach based on visual saliency and random forest from multi-temporal high-resolution remote-sensing images[J].International Journal of Remote Sensing,2018:1-24.
• [18] RODRIGUEZ-GALIANO V F,GHIMIRE B,ROGAN J,et al.An assessment of the effectiveness of a random forest classifier for land-cover classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2012,67:93-104.
• [19] 宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望[J].自动化学报,2013,39(6):730-744.(SONG Kechen,YAN Yunhui,CHEN Wenhui,et al.Research and perspective on local binary pattern[J].Acta Automatica Sinica,2013,39(6):730-744.)
• [20] HU Z,LI Q,ZOU Q,et al.Unsupervised simplification of image hierarchies via evolution analysis in scale-sets framework.[J].IEEE Transactions on Image Processing,2017,26(5):2394-2407.
• [21] JOHNSON B,XIE Z.Unsupervised image segmentation evaluation and refinement using a multi-scale approach[J].ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(4):473-483.
• [22] ESPINDOLA G M,CAMARA G,REIS I A,et al.Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation[J].International Journal of Remote Sensing,2006,27(14):3035-3040.
• [23] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.