本文關(guān)鍵詞： 混雜地物 同物異譜 決策樹分類 南方丘陵地區(qū)　出處：《國土資源遙感》2016年02期 　論文類型：期刊論文

【摘要】：復(fù)雜流域地物混雜,因受背景干擾,對混雜在不同背景地物中的目標(biāo)地物很難用1個規(guī)則區(qū)分出來�；贚andsat8多波段影像,以湘江的Ⅰ級支流蒸水河流域和長江三角洲的3大城市為研究區(qū),采用最大似然法進行初步分類;分析混雜地物的光譜特征,探討區(qū)分混雜地物的決策規(guī)則,對水體、人工建筑、耕地、裸地、林地和裸巖等基本地物進行分類。結(jié)果表明,蒸水河流域分類的整體精度達(dá)到88.21%,高于監(jiān)督分類精度(79.68%);其他3個長江三角洲城市的分類精度都在92%以上。所提出的混雜地物區(qū)分模型可以提高混雜在不同背景中的同類地物的分類精度。
[Abstract]:Because of the background interference, it is difficult to distinguish the target objects mixed in different background objects by one rule. Based on Landsat8 multi-band images, Taking the first grade tributary of Xiangjiang River as the study area and the three major cities of the Yangtze River Delta as the study areas, the maximum likelihood method is used to carry out the preliminary classification, and the spectral characteristics of the hybrid objects are analyzed, and the decision rules for distinguishing the mixed objects are discussed. Artificial buildings, cultivated land, bare land, woodland and bare rock are classified. The results show that, The overall classification accuracy of the Yunshui River Basin reaches 88.21, which is higher than that of the supervised classification accuracy of 79.68%, and the classification accuracy of the other three cities in the Yangtze River Delta is above 92%. The proposed hybrid ground feature classification model can be improved to be mixed in different backgrounds. The classification accuracy of the same kind of features.
【作者單位】： 河海大學(xué)地學(xué)院地理信息科學(xué)系;
【基金】：國家自然科學(xué)重點基金項目“半濕潤半干旱流域水文模型研究”(編號:41130639)資助
【分類號】：TP751

【相似文獻】

相關(guān)會議論文 前1條

1 高妙仙;毛政元;;Quick Bird影像城市建筑物光譜分析[A];圖像圖形技術(shù)與應(yīng)用進展——第三屆圖像圖形技術(shù)與應(yīng)用學(xué)術(shù)會議論文集[C];2008年

，

本文編號：1546751