【摘要】：本研究以哈爾濱市為研究區(qū),采用Landsat-8多光譜影像為數(shù)據(jù)源,計(jì)算出水體指數(shù)、植被指數(shù)、建筑指數(shù)和土壤指數(shù)等共20個(gè)地物光譜指數(shù);基于指數(shù)的決策樹(shù)分類方法提取土地覆被類型,并對(duì)分類結(jié)果進(jìn)行精度驗(yàn)證,對(duì)比分析不同指數(shù)對(duì)分類精度的影響。經(jīng)過(guò)精度對(duì)比、篩選五組數(shù)據(jù)作為變量用決策樹(shù)方法進(jìn)行分類,并與于單純地物光譜的(普通)決策樹(shù)分類結(jié)果和最大似然法相比較。結(jié)果顯示:五組基于指數(shù)的決策樹(shù)分類結(jié)果都比普通決策樹(shù)分類和傳統(tǒng)的最大似然法分類精度高,分類精度最高的一組與以上兩種分類結(jié)果相比,總精度分別提高了2.59%和9.55%,Kappa系數(shù)分別提高了0.08和0.15。本研究呈現(xiàn)了基于指數(shù)的決策樹(shù)分類方法在土地利用信息提取中的優(yōu)勢(shì),為更好協(xié)調(diào)哈爾濱市土地利用與城市擴(kuò)展提供研究依據(jù)。
[Abstract]:In this study, 20 spectral indices of water body, vegetation index, building index and soil index were calculated by using Landsat-8 multi-spectral image as data source and Harbin city as study area. The decision tree classification method based on index is used to extract land cover types, and the accuracy of classification results is verified, and the effects of different indices on classification accuracy are compared and analyzed. After precision comparison, five groups of data were selected as variables and classified by decision tree method, and compared with the classification results of the (common) decision tree and the maximum likelihood method. The results show that the classification accuracy of the five groups of decision trees based on index is higher than that of the ordinary decision trees and the traditional maximum likelihood method. The group with the highest classification accuracy is compared with the above two kinds of classification results. The total precision was increased by 2.59% and 9.55%, respectively, and the Kappa coefficient was increased by 0.08 and 0.15, respectively. This study presents the advantage of decision tree classification method based on index in extracting land use information, which provides a basis for better coordination of land use and urban expansion in Harbin.
【作者單位】： 哈爾濱師范大學(xué)地理科學(xué)學(xué)院;黑龍江省普通高等學(xué)校地理環(huán)境遙感監(jiān)測(cè)重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金(41571199) 黑龍江省自然科學(xué)基金項(xiàng)目(ZD201308);黑龍江省自然科學(xué)基金青年項(xiàng)目(QC2016050)
【分類號(hào)】：P237

【相似文獻(xiàn)】

相關(guān)期刊論文 前9條

1 陳云;戴錦芳;李俊杰;;基于影像多種特征的CART決策樹(shù)分類方法及其應(yīng)用[J];地理與地理信息科學(xué);2008年02期

2 閆利;孫穎超;;基于影像多種特征的決策樹(shù)分類方法[J];地理空間信息;2009年06期

3 張春森;馮麗;;結(jié)合時(shí)相和波譜信息的植被信息提取[J];測(cè)繪科學(xué);2010年05期

4 莊長(zhǎng)偉;歐陽(yáng)志云;徐衛(wèi)華;鄭華;王效科;白楊;;基于MODIS的海河流域生態(tài)系統(tǒng)空間格局[J];生態(tài)學(xué)雜志;2009年06期

5 劉清臣;張舞燕;孟秀軍;;一種干旱半干旱地區(qū)決策樹(shù)分類方法[J];測(cè)繪與空間地理信息;2014年07期

6 楊強(qiáng);張志;;湖北省�？盗椎V區(qū)開(kāi)采面及固體廢棄物遙感信息提取方法研究[J];國(guó)土資源遙感;2009年02期

7 姜玲;黃家柱;;一種研究城市化發(fā)展的新方法[J];地理與地理信息科學(xué);2007年04期

8 馮穩(wěn);張志;烏云其其格;孟丹;;采用決策樹(shù)分類方法進(jìn)行煤矸石信息提取研究[J];黑龍江大學(xué)自然科學(xué)學(xué)報(bào);2011年02期

9 ;[J];;年期

相關(guān)碩士學(xué)位論文 前1條

1 李麟青;基于普適特征的網(wǎng)絡(luò)流量決策樹(shù)分類方法[D];蘇州大學(xué);2012年

，

本文編號(hào)：2361867