摘要
以安庆市区的高分一号影像为信息源,结合地震应急基础统计数据资料,重点研究基于CART决策树的面向对象分类对研究区的建筑物进行分类提取,分类的总体精度和Kappa系数分别为83.9%和0.821。结果表明:基于CART决策树面向对象分类方法对研究区高分一号影像进行建筑物提取,分类精度较好,可作为地震应急基础数据库更新辅助手段之一。
Based on the high-score No. 1 image of Anqing city and the basic statistical data of earthquake emergency, the object-oriented classification based on CART decision tree is studied to extract the buildings in the study area. The overall accuracy and Kappa coefficient of the classification are 83.9% and 0.821,respectively. Results show that the object-oriented classification method based on CART decision tree can extract buildings from the high-score No. 1 image in the study area, and the classification accuracy is good. It can be used as one of the auxiliary means for updating the basic database of earthquake emergency response.
引文
[1]樊舒迪,胡月明,刘振华.一种新的面向对象城市建筑物信息提取方法研究[J].华南师范大学学报(自然科学版),2015,47(6):91-97.
[2]周亚男,沈占锋,骆剑承,等.阴影辅助下的面向对象城市建筑物提取[J].地理与地理信息科学,2010,26(3):37-40.
[3]郝兰朋.面向对象技术在城市建筑物提取中的应用研究[D].西安:西安科技大学,2011.
[4]齐乐,岳彩荣.基于CART决策树方法的遥感影像分类[J].林业调查规划,2011(4):63-66.
[5]汤国安.遥感数字图像处理[M].北京:科学出版社,2004.
[6]孙晓霞,张继贤,刘正军.利用面向对象的方法从IKONOS全色影像中提取河流和道路[J].测绘科学,2006,31(1):62-63.
[7]候伟,鲁学军,张春晓,等.面向对象的高分辨率影像信息提取方法研究——以四川理县居民地提取为例[J].地球信息科学学报,2010,12(1):119-125.
[8]陈鑫.基于决策树技术的遥感影像分类研究[D].南京:南京林业大学,2006.
[9]郝泷,陈永富,刘华,等.基于纹理信息CART决策树的林芝县森林植被面向对象分类[J].遥感技术于应用,2017,32(2):386-394.
[10] Aguilar M A. Saldana M M.Aguilar F J. GeoEye and World View-2 Pan-sharpened Imagery for Object-based Classification in Urban Environments[J]. International Journal of Remote Sensing,2013,34(7):2588-2606.
[11]陶超,谭毅华,蔡华杰,等.面向对象的高分辨率遥感影像城区建筑物分级提取方法[J].测绘学报,2010,39(1):39-45.