摘要
以达里诺尔湿地自然保护区为研究区,基于国产GF-1遥感影像,采用面向对象和传统目视解译的分类方法对研究区土地覆盖遥感信息进行提取,并对其结果进行对比分析,采取混淆矩阵对面向对象分类结果进行精度验证。结果表明:(1)充分利用了GF-1遥感影像的光谱信息,面向对象分类采取试错法确定最优分割尺度为550,形状和紧致度因子分别为0.6和0.5,各波段权重均为1;(2)面向对象分类总体分类精度达98.22%,KAPPA系数为0.96;(3)面向对象分类方法可快速准确提取类型较为复杂的土地覆盖信息,为内陆湿地精准快速提取研究区土地覆盖分类信息提供参考,以期为湿地遥感业务化监测提供技术规范。
Based on domestic GF-1 remote sensing imagery, taking the Darinor Wetland Nature Reserve as the research area, we extracted land cover remote sensing information by adopting object-oriented and traditional visual interpretation classification methods, and analyzed the results, verified the accuracy of the objectoriented classification results by using the confusion matrix. The results showed that:(1) spectral information of GF-1 remote sensing images was fully utilized, the object-oriented classification adopted trial-and-error method to determine the optimal segmentation scale as 550, and the shape and compactness factors was 0.6 and 0.5, respectively, and each band weight was 1;(2) the overall classification accuracy of object-oriented classification was up to 98.22%, and the KAPPA coefficient was about 0.96;(3) land cover information of relatively complex types was extracted by the object-oriented classification method quickly and accurately,which could be a reference for accurate and rapid extraction of land cover for the inland wetland, and provide technical specifications for wetland remote sensing operational monitoring.
引文
[1]吴亮,濮励杰,朱明.中日土地利用分类比较[J].中国土地科学,2010,24(7):77-80.
[2]李玉凤,刘红玉.湿地分类和湿地景观分类研究进展[J].湿地科学,2014,12(1):102-108.
[3]李培军,黄颖端.运用多层次迭代方法进行遥感数据的土地覆盖分类[J].自然科学进展,2004,14(5):588-592.
[4]侯伟,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.
[5]王文宇,李静.面向对象的高分辨率遥感影像土地覆盖信息提取[J].测绘科学,2008,33(S1):196-197.
[6]莫登奎,林辉,孙华等.基于高分辨率遥感影像的土地覆盖信息提取[J].遥感技术与应用,2005,20(4):411-414.
[7]陈文倩,丁建丽,王娇,等.基于高分一号影像的土地覆被分类方法初探[J].干旱区地理,2016,39(1):182-189.
[8]程乾,陈金凤.基于高分1号杭州湾南岸滨海陆地土地覆盖信息提取方法研究[J].自然资源学报,2015,30(2):350-360.
[9]李艳华,了建丽,闻人华.基于国产GF-1遥感影像的山区细小水体提取方法研究[J].资源科学,2015,37(2):408-416.
[10]陶舒,周旭,刘倩,等.面向对象的高分辨率遥感影像数据的道路提取流程[J].遥感信息,2015,30(6):76-80.
[11]刘书含,顾行发,余涛,等.高分一号多光谱遥感数据的面向对象分类[J].测绘科学,2014,39(12):91-94.
[12]宋军伟,张友静,李鑫川,等.基于GF-1与Landsat-8影像的土地覆盖分类比较[J].地理科学进展,2016,35(2):255-263.
[13]贾玉秋,李冰,程永政,等.基于GF-1与Landsat-8多光谱遥感影像的玉米LAI反演比较[J].农业工程学报,2015,31(9):173-179.
[14]杨长坤,王崇倡,张鼎凯,等.基于SVM的高分一号卫星影像分类[J].测绘与空间地理信息,2015,38(9):142-144.
[15]陈兴杰.基于GF-1号卫星影像的监督分类方法比较[J].矿山测量,2017,45(3):17-19.
[16]任建斌.基于小波变换和BP人工神经网络的遥感影像分类研究[D].呼和浩特:内蒙古师范大学,2012:1-55.
[17]杨玉霞.基于智能算法的土地覆盖分类研究[D].呼和浩特:内蒙古师范大学,2012:1-49.
[18]秦福莹,金凤,那音太,等.达里诺尔国家级自然保护区典型湿地植被群落光谱特征分析[J].内蒙古科技与经济,2016,6(11):32-33.
[19]胡凡盛,杨太保,王晶,等.基于面向对象分类的马兰冰帽变化与气候响应[J].干旱区研究,2017,34(5):1018-1026.
[20]苏晓玉,甘甫平,万里飞,等.辅以波谱分析的高分辨率影像面向对象分类研究[J].图学学报,2012,3(1):73-79.