本文關(guān)鍵詞： 高光譜遙感 HJ-A 農(nóng)作物分類 支持向量機(jī) 遺傳算法　出處：《遙感技術(shù)與應(yīng)用》2017年02期 　論文類型：期刊論文

【摘要】：利用高光譜遙感技術(shù)識別農(nóng)作物類型已經(jīng)成為高光譜遙感研究的熱點領(lǐng)域。以青海省湟水流域內(nèi)油菜、小麥和青稞等典型農(nóng)作物為分類對象,以HJ-1A HSI高光譜數(shù)據(jù)和GF-1 WFV高分辨率數(shù)據(jù)為數(shù)據(jù)源,探討利用高光譜遙感影像進(jìn)行農(nóng)作物類型信息提取的方法。數(shù)據(jù)經(jīng)預(yù)處理后,首先,利用WFV數(shù)據(jù)采用面向?qū)ο蠓椒ㄌ崛⊙芯繀^(qū)農(nóng)作物種植邊界,并利用其對HSI高光譜影像進(jìn)行種植區(qū)域提取;其次,將提取后的高光譜影像經(jīng)數(shù)據(jù)形式變換獲得包括:R、1/R、Log(R)、d(R)、d(Log(R))和CR共6種數(shù)據(jù)形式;最后,利用上述6種數(shù)據(jù)形式的全波段數(shù)據(jù)和經(jīng)遺傳算法GA-SVM進(jìn)行光譜波段選取后的6種特征數(shù)據(jù),采用支持向量機(jī)SVM方法進(jìn)行農(nóng)作物分類。結(jié)果表明:采用基于樣本的面向?qū)ο蠓诸惙椒ㄌ崛「匦畔⒕雀咔覍崿F(xiàn)周期短;利用GA-SVM波段選取后的6種特征數(shù)據(jù)集進(jìn)行農(nóng)作物分類,其精度顯著高于全波段數(shù)據(jù)集分類精度;6種數(shù)據(jù)變換形式中,d(Log(R))和CR是兩種最優(yōu)的高光譜分類數(shù)據(jù)形式,其全波段和特征波段數(shù)據(jù)進(jìn)行農(nóng)作物分類均能獲得較好的分類精度,總體精度最高分別達(dá)88%和86%,而采用1/R、Log(R)和R數(shù)據(jù)形式需經(jīng)GA-SVM光譜波段選取后才能獲得較優(yōu)分類精度。
[Abstract]:Using hyperspectral remote sensing technology to identify crop types has become a hot research area of hyperspectral remote sensing. Typical crops such as rape wheat and highland barley in Huangshui basin of Qinghai Province are taken as classification objects. Using HJ-1A HSI hyperspectral data and GF-1 WFV high-resolution data as data sources, the method of extracting crop type information from hyperspectral remote sensing images is discussed. Firstly, WFV data are used to extract the crop planting boundary in the study area, and the HSI hyperspectral image is used to extract the planting area. Secondly, the extracted hyperspectral images were transformed into six data forms, including 1 / 1 / R ~ (1 / R) / R ~ (1 / R) and CR (R ~ (1 / R) ~ (1 / R) / R ~ (1 / R) / R ~ (1 / R) / R ~ (1 / R)). Finally, the full band data of the above six data forms and the six characteristic data after the spectral band selection by genetic algorithm (GA-SVM) are used. The SVM method of support vector machine is used to classify crops. The results show that the method of object-oriented classification based on samples has high precision and short realization period. The precision of crop classification is significantly higher than that of the whole band data set by using the 6 characteristic data sets selected from GA-SVM band. Among the six kinds of data transformation, the two optimal hyperspectral classification data forms are Dendrogram (RU) and CR. The classification accuracy of the whole band and characteristic band data for crop classification can be obtained. The total precision is up to 88% and 86, respectively, and the best classification accuracy can be obtained by using 1 / R R) and R data after the GA-SVM spectral band is selected.
【作者單位】： 青海師范大學(xué)生命與地理科學(xué)學(xué)院青海省自然地理與環(huán)境過程重點實驗室;
【基金】：國家自然科學(xué)基金項目(40861022、41550003) 青海省重點實驗室發(fā)展專項(2014-Z-Y24、2015-Z-Y01)
【分類號】：S127;TP751
【正文快照】： 1引言農(nóng)作物識別與分類是農(nóng)業(yè)遙感的基礎(chǔ),是農(nóng)情遙感監(jiān)測的重要內(nèi)容,高效、準(zhǔn)確地提取農(nóng)作物種植面積、結(jié)構(gòu)和類型分布信息對于國家糧食安全、社會經(jīng)濟(jì)穩(wěn)定、農(nóng)業(yè)政策制定等均具有重要意義[1]。受我國農(nóng)作物種植分散性、類型多樣化和地域復(fù)雜性影響,采用常規(guī)的地面調(diào)查方法獲，

本文編號：1443237