發(fā)布時間：2018-03-06 21:23

  本文選題：單變量特征選擇　切入點：光譜特征　出處：《遙感學報》2017年04期 　論文類型：期刊論文

【摘要】：遙感識別多源特征綜合和特征優(yōu)選是提高遙感影像分類精度的關鍵技術。農(nóng)作物遙感識別中,識別特征的相對單一和數(shù)量過多均會導致作物識別精度不理想。隨機森林(random forests)采用分類與回歸樹(CART)算法來生成分類樹,結合了bagging和隨機選擇特征變量的優(yōu)點,是一種有效的分類方法。單變量特征選擇(univariate feature selection)能夠?qū)γ恳粋�待分類的特征進行測試,衡量該特征和響應變量之間的關系,根據(jù)得分舍棄不好的特征,優(yōu)選得到的特征用于分類。本文基于隨機森林和單變量特征選擇,利用多時相光譜信息、植被指數(shù)信息、紋理信息及波段差值信息,設計多組分類實驗方案,對江蘇省泗洪縣的高分一號(GF-1)和環(huán)境一號(HJ-1A)影像進行分類研究,旨在選擇最佳的分類方案對實驗區(qū)主要農(nóng)作物進行識別和提取。實驗結果表明:(1)多源信息綜合的農(nóng)作物分類精度明顯高于單一的原始光譜特征分類,說明不同類型特征的引入能改善分類效果;(2)基于單變量特征選擇算法的優(yōu)選特征分類效果最佳,總體精度97.07%,Kappa系數(shù)0.96,表明了特征優(yōu)選在降低維度的同時,也保證了較高的分類精度。隨機森林和單變量特征選擇結合的方法可以提高遙感影像的分類精度,為農(nóng)作物的識別和提取研究提供了有效的方法。
[Abstract]:Multi-source feature synthesis and feature optimization of remote sensing recognition are the key technologies to improve the classification accuracy of remote sensing image. The relative singularity and excessive number of recognition features will lead to unsatisfactory crop recognition accuracy. Random forest random forestsuses the classification and regression tree cart algorithm to generate the classification tree, which combines the advantages of bagging and random selection of feature variables. Univariate feature selection) can test each feature to be classified, measure the relationship between the feature and the response variable, and discard the bad feature according to the score. The selected features are used for classification. Based on the random forest and single variable feature selection, this paper designs a multi-group classification experiment scheme based on multitemporal spectral information, vegetation index information, texture information and band difference information. The classification of Gaofen No. 1 (GF-1) and environmental No. 1 (HJ-1A) images of Sihong County, Jiangsu Province, were studied. In order to select the best classification scheme for the identification and extraction of the main crops in the experimental area, the experimental results show that the classification accuracy of the multi-source information synthesis is obviously higher than that of the single original spectral feature classification. It shows that the introduction of different types of features can improve the classification effect.) the optimal feature classification effect based on single variable feature selection algorithm is the best, and the overall accuracy is 97.07 and Kappa coefficient 0.96, which indicates that feature selection can reduce the dimension at the same time. The combination of random forest and single variable feature selection can improve the classification accuracy of remote sensing images and provide an effective method for crop identification and extraction.
【作者單位】： 中國科學院遙感與數(shù)字地球研究所再生資源實驗室;中國科學院大學資源與環(huán)境學院;
【基金】：國家自然科學基金(編號:41571422,41301497)~~
【分類號】：TP751

【參考文獻】

相關期刊論文 前9條

1 程希萌;沈占鋒;邢廷炎;夏列鋼;吳田軍;;基于mRMR特征優(yōu)選算法的多光譜遙感影像分類效率精度分析[J];地球信息科學學報;2016年06期

2 楊佒雯;張錦水;朱秀芳;謝登峰;袁周米琪;;隨機森林在高光譜遙感數(shù)據(jù)中降維與分類的應用[J];北京師范大學學報(自然科學版);2015年S1期

3 馬s，

本文編號：1576571