本文選題：高光譜遙感 + 數(shù)據(jù)挖掘　； 參考：《大連海事大學(xué)》2014年博士論文

【摘要】：高光譜遙感數(shù)據(jù)的特征提取和分類(lèi)工作是高光譜遙感應(yīng)用領(lǐng)域的研究重點(diǎn)和熱點(diǎn)。濱海濕地區(qū)域面積廣闊、地物分布復(fù)雜多樣,且高光譜遙感數(shù)據(jù)本身維度高、數(shù)據(jù)量大,導(dǎo)致傳統(tǒng)的特征提取方法對(duì)于蘊(yùn)含于高光譜數(shù)據(jù)中的光譜特征信息利用有限,對(duì)于專(zhuān)家經(jīng)驗(yàn)知識(shí)和統(tǒng)計(jì)信息以外的潛在特征,難以充分提取,進(jìn)而難以形成適用于濱海濕地高光譜遙感數(shù)據(jù)的高精度分類(lèi)算法。這不利于高光譜遙感技術(shù)在濱海濕地遙感研究領(lǐng)域的深入發(fā)展。 本文的工作主要面向?yàn)I海濕地植被高光譜遙感精細(xì)化監(jiān)測(cè)的需求,以黃河三角洲濕地為研究區(qū)域,利用高光譜遙感影像和現(xiàn)場(chǎng)采集的典型植被現(xiàn)場(chǎng)光譜數(shù)據(jù),發(fā)展了基于數(shù)據(jù)挖掘技術(shù)的濱海濕地典型植被高光譜特征提取和分類(lèi)方法,實(shí)現(xiàn)針對(duì)研究區(qū)域典型植被與地物類(lèi)型的高精度提取和分類(lèi)。具體內(nèi)容如下： (1)開(kāi)展了基于光譜可分性與季節(jié)光譜特征差異的現(xiàn)場(chǎng)光譜特征分析 針對(duì)研究區(qū)域和高光譜遙感影像的特點(diǎn),開(kāi)展黃河三角洲濱海濕地典型植被現(xiàn)場(chǎng)光譜測(cè)量,得到了對(duì)研究區(qū)域植被類(lèi)型光譜特征代表性良好的現(xiàn)場(chǎng)光譜數(shù)據(jù)；利用現(xiàn)場(chǎng)實(shí)測(cè)的典型植被光譜數(shù)據(jù),開(kāi)展基于反射率光譜的植被光譜分析和特征提取。為分析不同植被光譜間的可分性特征,發(fā)展了一種基于包絡(luò)線(xiàn)去除光譜差值的特征波段提取方法,獲得了典型植被的波段可分性查找表；為分析不同植被不同季節(jié)的光譜特征差異,基于導(dǎo)數(shù)變換方法開(kāi)展典型植被春、秋兩季光譜特征分析比較工作,獲得了綠光反射峰、紅光吸收峰、紅邊和近紅外反射峰等4種光譜特征的位置和反射率差異信息。 (2)發(fā)展了基于數(shù)據(jù)挖掘的研究區(qū)域典型植被高光譜遙感特征提取技術(shù) 針對(duì)PROBA CHRIS多視角高光譜遙感衛(wèi)星影像,首先研究了該影像數(shù)據(jù)的預(yù)處理技術(shù),并對(duì)不同視角影像的成像效果及分類(lèi)能力進(jìn)行分析研究,確定0°視角影像作為特征提取的數(shù)據(jù)源。在此基礎(chǔ)上,為獲取高光譜遙感影像中典型植被的遙感光譜特征和特征波段組合規(guī)律,指導(dǎo)研究區(qū)域典型植被遙感分類(lèi),發(fā)展了一種基于關(guān)聯(lián)規(guī)則挖掘的濱海濕地典型植被高光譜遙感特征提取技術(shù),利用關(guān)聯(lián)規(guī)則挖掘中的廣義規(guī)則歸納算法,配合關(guān)聯(lián)規(guī)則定量指標(biāo)分析,獲得了研究區(qū)域8類(lèi)典型植被與地物類(lèi)型(包括蘆葦、檉柳、堿蓬、大米草、清澈水體、渾濁水體、裸灘、裸地)的高光譜遙感特征集。該技術(shù)能夠充分提取高光譜遙感數(shù)據(jù)中的潛在特征,并滿(mǎn)足光譜特征在分類(lèi)、波段和信息等多個(gè)維度的獨(dú)立性要求。 (3)發(fā)展了基于決策樹(shù)的研究區(qū)域典型植被高光譜遙感分層分類(lèi)方法 針對(duì)覆蓋研究區(qū)域的PROBA CHRIS高光譜遙感數(shù)據(jù),基于本文所建立的典型植被與地物類(lèi)型高光譜遙感特征集,并結(jié)合現(xiàn)場(chǎng)光譜特征波段信息,確定研究區(qū)域8類(lèi)典型植被與地物類(lèi)型高光譜遙感分類(lèi)規(guī)則,發(fā)展了一種基于決策樹(shù)的黃河三角洲典型植被高光譜遙感分層分類(lèi)方法。利用該方法對(duì)PROBA CHRIS高光譜遙感影像進(jìn)行分類(lèi)實(shí)驗(yàn),將整景影像分為8類(lèi)典型植被與地物類(lèi)型,利用現(xiàn)場(chǎng)踏勘信息結(jié)合高空間分辨率遙感影像解譯所獲取的標(biāo)準(zhǔn)解譯圖像,對(duì)分類(lèi)結(jié)果進(jìn)行精度評(píng)價(jià),并與基于相同訓(xùn)練樣本的SVM分類(lèi)結(jié)果進(jìn)行對(duì)比,實(shí)驗(yàn)結(jié)果顯示,本文所發(fā)展的分類(lèi)方法其分類(lèi)精度較SVM算法有明顯提高,超過(guò)10%。
[Abstract]:The feature extraction and classification of hyperspectral remote sensing data is the focal point and hotspot in the field of hyperspectral remote sensing application .

The work of this paper mainly focuses on the demand of high spectral remote sensing precision monitoring of coastal wetland vegetation , uses the Yellow River Delta wetland as the research area , develops the typical vegetation hyperspectral feature extraction and classification method based on data mining technology using hyperspectral remote sensing image and typical vegetation field spectral data collected on site , and realizes high - precision extraction and classification of typical vegetation and figure types in the study area .

( 1 ) On - site spectral characteristic analysis based on spectral variability and seasonal spectral characteristics is carried out .

According to the characteristics of the research area and hyperspectral remote sensing image , the field spectral measurement of typical vegetation in the coastal wetland of the Yellow River Delta was carried out .
The vegetation spectral analysis and feature extraction based on reflectance spectra are carried out by using typical vegetation spectral data measured on site . In order to analyze the variability of vegetation spectra , a feature band extraction method based on envelope removal spectral difference is developed , and the band - separable look - up table of typical vegetation is obtained .
In order to analyze the spectral characteristic difference of different vegetation seasons , the spectral characteristic analysis of typical vegetation spring and autumn is carried out based on derivative transform method , and the position and reflectivity difference information of four spectral features , such as green reflection peak , red absorption peak , red edge and near infrared reflection peak are obtained .

( 2 ) The technology of hyperspectral remote sensing feature extraction based on data mining is developed .

In this paper , a high spectral remote sensing feature set of typical vegetation in coastal wetland , which is based on correlation rule mining , is developed , and the high spectral remote sensing feature set based on correlation rule mining is developed .

( 3 ) The hierarchical classification method of hyperspectral remote sensing based on decision tree is developed .

Based on the hyperspectral remote sensing feature set of typical vegetation and figure types established in this paper , the high spectral remote sensing classification rules of typical vegetation and ground objects in the study area are established based on the high spectral remote sensing feature set of typical vegetation and figure types established in this paper . The classification results are evaluated by using the method . The results show that the classification accuracy of the classification method is obviously improved compared with the SVM algorithm , which is more than 10 % .

【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TP79

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王明常;王亞楠;陳圣波;路鵬;陶玉龍;徐連舉;;多角度高光譜CHRIS/Proba植被模式數(shù)據(jù)大氣校正[J];吉林大學(xué)學(xué)報(bào)(地球科學(xué)版);2011年02期

2 張建鋒,邢尚軍,郗金標(biāo),宋玉民,馬丙堯;黃河三角洲可持續(xù)發(fā)展面臨的環(huán)境問(wèn)題與林業(yè)對(duì)策[J];東北林業(yè)大學(xué)學(xué)報(bào);2002年06期

3 劉慶生,劉高煥,勵(lì)惠國(guó);近、現(xiàn)代黃河三角洲地貌形態(tài)反演[J];地理與地理信息科學(xué);2003年02期

4 溫興平;胡光道;楊曉峰;;基于光譜特征擬合的高光譜遙感影像植被覆蓋度提取[J];地理與地理信息科學(xué);2008年01期

5 王霄鵬;張杰;馬毅;任廣波;;不同極化方式SAR與TM融合影像濱海濕地分類(lèi)精度比較[J];海洋學(xué)研究;2014年01期

6 許將軍;趙輝;;高光譜遙感圖像特征提取及分類(lèi)研究——基于離散余弦變換(DCT)及支撐向量機(jī)技術(shù)[J];佳木斯大學(xué)學(xué)報(bào)(自然科學(xué)版);2006年04期

7 帥艷民,朱啟疆,王培娟,王錦地,劉素紅,白香花;地物波譜數(shù)據(jù)倉(cāng)庫(kù)系統(tǒng)設(shè)計(jì)研究[J];計(jì)算機(jī)工程與應(yīng)用;2003年33期

8 劉敬;;基于direct LDA的高光譜遙感影像地物分類(lèi)[J];計(jì)算機(jī)科學(xué);2011年12期

9 劉敬;;核Direct LDA子空間高光譜影像地物分類(lèi)[J];計(jì)算機(jī)科學(xué);2012年06期

10 劉克;趙文吉;郭逍宇;胡德勇;宮兆寧;龍娟;;野鴨湖典型濕地植物光譜特征[J];生態(tài)學(xué)報(bào);2010年21期

，

本文編號(hào)：1889939