【摘要】：在我國北方旱地秋收作物生長關(guān)鍵期,云雨天氣影響較大,無法及時、有效地獲取光學(xué)遙感數(shù)據(jù),因此利用雷達(dá)遙感進(jìn)行旱地作物識別研究非常必要。文章以河北省衡水市為研究區(qū),選擇6期RADARAST-2全極化影像作為數(shù)據(jù)源,分類方法為隨機森林法。首先通過對比不同時相間的組合結(jié)果,優(yōu)選出了研究區(qū)典型秋收作物(玉米、棉花)的最佳識別時相及組合方式。其次,提取最優(yōu)識別時相的后向散射信息、紋理信息、極化分解等3部分信息,依據(jù)信息間相互組合的結(jié)果及隨機森林算法對變量的重要性評價,文中對上述3部分信息進(jìn)行了重要性評估。結(jié)果表明:利用SAR識別旱地秋收作物時應(yīng)著重關(guān)注作物生長前期的時相,其中玉米在6月27日單一時相下就可獲得90%以上的高精度;棉花面積小、地塊破碎,但通過6月3日與6月27日兩個時相的結(jié)合也得到了70%以上的精度。在玉米識別中極化信息具有較大的貢獻(xiàn),極化變量的加入主要增加了玉米和建筑用地的可分離性,與單純利用后向散射信息分類相比精度提高了近7%;同樣,紋理信息和極化分解信息的加入也使棉花的精度提高了3%。最后,利用隨機森林算法對變量的重要性評價機制,優(yōu)選出對玉米識別最為重要的5個變量,依次為:VH、Alpha、Yamaguchi4-Odd、Freeman-Vol和Mean(HV)。該研究利用雷達(dá)數(shù)據(jù)進(jìn)行旱地作物識別,驗證了雷達(dá)影像對旱地秋收作物的識別能力,不僅保證了數(shù)據(jù)獲取與天氣狀況的獨立性,還憑借SAR獨有的數(shù)據(jù)獲取方式,為光學(xué)數(shù)據(jù)提供了補充。
[Abstract]:In the key period of autumn crop growth in the north of China, cloud and rain weather have great influence on crop growth, so it is very necessary to use radar remote sensing to identify crops in drylands because it is difficult to obtain optical remote sensing data in time and effectively. In this paper, Hengshui City, Hebei Province is chosen as the study area, 6-phase RADARAST-2 polarimetric images are selected as the data source, and the classification method is the random forest method. Firstly, by comparing the results of different interphase combinations, the optimal identification time phase and combination mode of typical autumn harvest crops (maize, cotton) in the study area were optimized. Secondly, we extract the backscattering information, texture information and polarization decomposition information of the optimal identification phase, and evaluate the importance of random forest algorithm to the variables according to the results of the combination of the information and the random forest algorithm. In this paper, the importance of the above three parts of information is evaluated. The results showed that when using SAR to identify the crops in dry land, we should pay more attention to the early phase of crop growth, in which maize could get more than 90% high precision under the single phase on June 27. The cotton area is small and the block is broken, but through the combination of June 3 and June 27, more than 70% precision has been obtained. Polarization information plays an important role in maize recognition. The polarization variable mainly increases the separability of maize and construction land, and the precision is improved by 7% compared with the classification of backscatter information. Similarly, the addition of texture information and polarization decomposition information also increased the accuracy of cotton by 3%. Finally, using the stochastic forest algorithm to evaluate the importance of variables, the five most important variables for maize identification are selected, which are: VH,Alpha,Yamaguchi4-Odd,Freeman-Vol and Mean (HV). This study uses radar data to identify dryland crops, validates the ability of radar images to identify dryland autumn crops, not only ensures the independence of data acquisition and weather conditions, but also relies on the unique data acquisition method of SAR. It provides a supplement to the optical data.
【作者單位】： 中國農(nóng)業(yè)科學(xué)院農(nóng)業(yè)資源與農(nóng)業(yè)區(qū)劃研究所;農(nóng)業(yè)部農(nóng)業(yè)信息技術(shù)重點實驗室;
【基金】：國家科技重大專項項目“高分農(nóng)業(yè)遙感監(jiān)測與評價示范系統(tǒng)”(09-Y30B03-9001-13/15)
【分類號】：S127

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁婭萍;陳仲新;;基于最小距離法的RADARSAT-2遙感數(shù)據(jù)旱地作物識別[J];中國農(nóng)業(yè)資源與區(qū)劃;2014年06期

2 王迪;周清波;陳仲新;劉佳;;基于合成孔徑雷達(dá)的農(nóng)作物識別研究進(jìn)展[J];農(nóng)業(yè)工程學(xué)報;2014年16期

3 李志鵬;李正國;劉珍環(huán);吳文斌;譚杰揚;楊鵬;;基于中分辨TM數(shù)據(jù)的水稻提取方法對比研究[J];中國農(nóng)業(yè)資源與區(qū)劃;2014年01期

4 董師師;黃哲學(xué);;隨機森林理論淺析[J];集成技術(shù);2013年01期

5 李坤;邵蕓;張風(fēng)麗;;基于RadarSat-2全極化數(shù)據(jù)的水稻識別[J];遙感技術(shù)與應(yīng)用;2012年01期

6 化國強;肖靖;黃曉軍;陳爾學(xué);李秉柏;;基于全極化SAR數(shù)據(jù)的玉米后向散射特征分析[J];江蘇農(nóng)業(yè)科學(xué);2011年03期

7 汪小欽;王欽敏;史曉明;凌飛龍;朱曉鈴;;基于主成分變換的ASAR數(shù)據(jù)水稻種植面積提取[J];農(nóng)業(yè)工程學(xué)報;2008年10期

8 楊沈斌;李秉柏;申雙和;譚炳香;何維;;基于多時相多極化差值圖的稻田識別研究[J];遙感學(xué)報;2008年04期

9 楊沈斌;李秉柏;申雙和;譚炳香;何維;王志明;;基于ENVISAT ASAR數(shù)據(jù)的水稻遙感監(jiān)測[J];江蘇農(nóng)業(yè)學(xué)報;2008年01期

10 凌飛龍;汪小欽;史曉明;;多時相SAR圖像水稻分布信息提取方法研究[J];福建師范大學(xué)學(xué)報(自然科學(xué)版);2007年03期

【共引文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李磊;牟少敏;林中琦;;隨機森林在棉蚜蟲害等級預(yù)測中的應(yīng)用[J];安徽農(nóng)學(xué)通報;2017年01期

2 王錚;任華;方燕萍;;隨機森林在運營商大數(shù)據(jù)補全中的應(yīng)用[J];電信科學(xué);2016年12期

3 宋建國;高強山;李哲;;隨機森林回歸在地震儲層預(yù)測中的應(yīng)用[J];石油地球物理勘探;2016年06期

4 許t，

本文編號：2443394