基于随机森林的FY-2G云检测方法
|
摘要
根据遥感影像中云检测原理,提出了基于随机森林的遥感影像云检测方法,并将其应用于FY-2G影像。结合国家气象卫星中心(NSMC)的云检测产品数据进行了算法的精度检验,云检测个例的精度检验结果显,最高命中率(POD)为88.32%,最低误报率(FAR)为9.36%,临界成功指数(CSI)为80.14%。结果表明,该方法有效地提高了云检测精度,同时能正确标识NSMC中部分误判的情况。
According to the principle of cloud detection in remote sensing images,a method based on the random forest was proposed in this paper and applied to FY-2 G images. Combining the cloud inspection product of the National Meteorological Satellite Center( NSMC) for accuracy testing of the algorithm,the accuracy test of the cloud detection shows that the Probability of Detection( POD)is 88.32%,the minimum False Alarm Rate( FAR) is 9.36%,and the Critical Success Index( CSI) is 80.14%. The results show that the method can improve the accuracy of cloud detection effectively,and identify the partial misjudgment in NSMC correctly.
According to the principle of cloud detection in remote sensing images,a method based on the random forest was proposed in this paper and applied to FY-2 G images. Combining the cloud inspection product of the National Meteorological Satellite Center( NSMC) for accuracy testing of the algorithm,the accuracy test of the cloud detection shows that the Probability of Detection( POD)is 88.32%,the minimum False Alarm Rate( FAR) is 9.36%,and the Critical Success Index( CSI) is 80.14%. The results show that the method can improve the accuracy of cloud detection effectively,and identify the partial misjudgment in NSMC correctly.
引文
[1]曹敏洁.遥感图像厚云及其阴影去除技术研究[D].桂林:广西师范大学,2015.
[2]施鹏.基于光学遥感图像的舰船目标自动检测技术[D].合肥:中国科学技术大学,2010.
[3]邱康睦,王宝华,吴晓.气象卫星遥感海面温度的资料处理方法[J].中国空间科学技术,1992(1):67-73.
[4]YAN Z,BAOGUO W U,DONG W.Research dynamics of the classification methods of remote sensing images[J].Asian Agricultural Research,2013,5(3):118-122.
[5]WANG K,GU X,YU T,et al.Classification of hyperspectral remote sensing images using frequency spectrum similarity[J].Science China(Technological Sciences),2013(4):980-988.
[6]刘奇,傅云飞,冯沙.基于ISCCP观测的云量全球分布及其在NCEP再分析场中的指示[J].气象学报,2010(5):689-704.
[7]王燕,王伯民.ISCCP产品和我国地面观测总云量差异[J].应用气象学报,2009,20(4):411-418.
[8]刘紫涵,吴艳兰.遥感图像云检测方法研究进展[J].国土资源遥感,2017,29(4):6-12.
[9]侯舒维,孙文方,郑小松.遥感图像云检测方法综述[J].空间电子技术,2014(3):68-76.
[10]武艳,银燕,师春香,等.基于动态阈值法的NOAA系列卫星云检测结果检验[J].高原气象,2012(3):745-751.
[11]韩杰,杨磊库,李慧芳,等.基于动态阈值的HJ-1B图像云检测算法研究[J].国土资源遥感,2012,24(2):12-18.
[12]杨俊,吕伟涛,马颖,等.基于自适应阈值的地基云自动检测方法[J].应用气象学报,2009,20(6):713-721.
[13]杨羚,王树根,孙明伟,等.基于图割模型的高分全色影像自动云检测[J].地理空间信息,2018,16(1):12-15.
[14]LI D,YANG F,WANG X.Study on ensemble crop information extraction of remote sensing images based on SVM and BPNN[J].Journal of the Indian Society of Remote Sensing,2017:229-237.
[15]GAO F,ZHANG L,WANG J,et al.Change detection in remote sensing images of damage areas with complex terrain using texture information and SVM[C]∥Proceedings of 2015 International Conference on Circuits and Systems(CAS 2015).Beijing:[s.n.],2015:225-229.
[16]WANG P,BAO W.Wetland information extraction from RS image based on wavelet packet and the active learning support vector machine[C]∥Computer and Computing Technologies in Agriculture IV.Berlin:Springer,2011:491-499.
[17]周天宁,明冬萍,赵睿.参数优化随机森林算法的土地覆盖分类[J].测绘科学,2017,42(2):88-94.
[18]张晓羽,李凤日,甄贞,等.基于随机森林模型的陆地卫星-8遥感影像森林植被分类[J].东北林业大学学报,2016,44(6):53-57.
[19]王书玉,张羽威,于振华.基于随机森林的洪河湿地遥感影像分类研究[J].测绘与空间地理信息,2014,37(4):83-85.
[20]吴丹,蔡晓东,谢月飞,等.基于直方图分析和OTSU算法的文字图像二值化[J].计算机与现代化,2013(7):117-119.
[2]施鹏.基于光学遥感图像的舰船目标自动检测技术[D].合肥:中国科学技术大学,2010.
[3]邱康睦,王宝华,吴晓.气象卫星遥感海面温度的资料处理方法[J].中国空间科学技术,1992(1):67-73.
[4]YAN Z,BAOGUO W U,DONG W.Research dynamics of the classification methods of remote sensing images[J].Asian Agricultural Research,2013,5(3):118-122.
[5]WANG K,GU X,YU T,et al.Classification of hyperspectral remote sensing images using frequency spectrum similarity[J].Science China(Technological Sciences),2013(4):980-988.
[6]刘奇,傅云飞,冯沙.基于ISCCP观测的云量全球分布及其在NCEP再分析场中的指示[J].气象学报,2010(5):689-704.
[7]王燕,王伯民.ISCCP产品和我国地面观测总云量差异[J].应用气象学报,2009,20(4):411-418.
[8]刘紫涵,吴艳兰.遥感图像云检测方法研究进展[J].国土资源遥感,2017,29(4):6-12.
[9]侯舒维,孙文方,郑小松.遥感图像云检测方法综述[J].空间电子技术,2014(3):68-76.
[10]武艳,银燕,师春香,等.基于动态阈值法的NOAA系列卫星云检测结果检验[J].高原气象,2012(3):745-751.
[11]韩杰,杨磊库,李慧芳,等.基于动态阈值的HJ-1B图像云检测算法研究[J].国土资源遥感,2012,24(2):12-18.
[12]杨俊,吕伟涛,马颖,等.基于自适应阈值的地基云自动检测方法[J].应用气象学报,2009,20(6):713-721.
[13]杨羚,王树根,孙明伟,等.基于图割模型的高分全色影像自动云检测[J].地理空间信息,2018,16(1):12-15.
[14]LI D,YANG F,WANG X.Study on ensemble crop information extraction of remote sensing images based on SVM and BPNN[J].Journal of the Indian Society of Remote Sensing,2017:229-237.
[15]GAO F,ZHANG L,WANG J,et al.Change detection in remote sensing images of damage areas with complex terrain using texture information and SVM[C]∥Proceedings of 2015 International Conference on Circuits and Systems(CAS 2015).Beijing:[s.n.],2015:225-229.
[16]WANG P,BAO W.Wetland information extraction from RS image based on wavelet packet and the active learning support vector machine[C]∥Computer and Computing Technologies in Agriculture IV.Berlin:Springer,2011:491-499.
[17]周天宁,明冬萍,赵睿.参数优化随机森林算法的土地覆盖分类[J].测绘科学,2017,42(2):88-94.
[18]张晓羽,李凤日,甄贞,等.基于随机森林模型的陆地卫星-8遥感影像森林植被分类[J].东北林业大学学报,2016,44(6):53-57.
[19]王书玉,张羽威,于振华.基于随机森林的洪河湿地遥感影像分类研究[J].测绘与空间地理信息,2014,37(4):83-85.
[20]吴丹,蔡晓东,谢月飞,等.基于直方图分析和OTSU算法的文字图像二值化[J].计算机与现代化,2013(7):117-119.