基于SVM雷達(dá)臥龍大熊貓棲息地森林成圖
發(fā)布時(shí)間:2018-09-01 16:24
【摘要】:臥龍自然保護(hù)區(qū)(世界自然遺產(chǎn)地)是大熊貓最主要的棲息地之一。結(jié)合雷達(dá)遙感全天時(shí)、全天候觀測(cè)優(yōu)勢(shì),以及森林覆蓋對(duì)棲息地生境評(píng)價(jià)的重要性,開展多時(shí)相、雙極化雷達(dá)數(shù)據(jù)森林精細(xì)成圖研究就顯得尤為重要。本研究首先對(duì)雷達(dá)數(shù)據(jù)進(jìn)行輻射地形校正;然后選用5個(gè)時(shí)相ALOS PALSAR數(shù)據(jù),采用支持向量機(jī)(support vector machine,SVM)方法進(jìn)行森林精細(xì)成圖。研究選取了5個(gè)多時(shí)相、雙極化典型特征信息參與初始訓(xùn)練和分類,即HH_m,HV_m,TSD,HH_m-HV_m和HH_m/HV_m;接著通過對(duì)不同信息組合分類精度的試驗(yàn)與對(duì)比,獲取了最優(yōu)特征組合HH_m,HV_m,TSD,HH_m-HV_m。對(duì)應(yīng)分類總體精度、森林及非森林類別用戶精度分別為86.90%,82.34%和92.83%,顯著優(yōu)于單時(shí)相單極化數(shù)據(jù)分類結(jié)果(分類總體精度55.47%)。研究結(jié)果驗(yàn)證了多時(shí)相、雙極化雷達(dá)遙感數(shù)據(jù)在自然遺產(chǎn)地森林精細(xì)成圖中的有效性,并揭示了雷達(dá)遙感在多云多雨地區(qū)生境監(jiān)測(cè)與評(píng)價(jià)中的潛力與應(yīng)用價(jià)值。
[Abstract]:Wolong Nature Reserve is one of the most important habitats for giant pandas. Combined with the advantages of radar remote sensing all day, all weather observation and the importance of forest cover to habitat evaluation, it is very important to study the precise mapping of forest with multi-phase and dual-polarization radar data. In this study, the radar data were first corrected by radiometric topography, and then five time-phase ALOS PALSAR data were selected, and the support vector machine (support vector machine,SVM) method was used for fine forest mapping. In this study, five multi-phase and two-polarization typical feature information were selected to participate in the initial training and classification. Then, HH_m,HV_m,TSD,HH_m-HV_m and HH_m/HV_m; obtained the optimal feature combination HH_m,HV_m,TSD,HH_m-HV_m. by the experiment and comparison of the classification accuracy of different information combinations. The accuracy of forest and non-forest users was 86.90% and 92.83% respectively, which was significantly better than that of single time and single polarization data (total classification accuracy was 55.47%). The results verify the validity of multi-temporal and dual-polarization radar remote sensing data in the fine forest mapping of natural heritage areas, and reveal the potential and application value of radar remote sensing in monitoring and evaluation of habitats in cloudy and rainy areas.
【作者單位】: 中國科學(xué)院遙感與數(shù)字地球研究所數(shù)字地球重點(diǎn)實(shí)驗(yàn)室;中國科學(xué)院大學(xué);聯(lián)合國教科文組織國際自然與文化遺產(chǎn)空間技術(shù)中心;山東科技大學(xué)測(cè)繪科學(xué)與工程學(xué)院;
【基金】:國家國際科技合作專項(xiàng)項(xiàng)目“全球變化對(duì)世界遺產(chǎn)影響空間精細(xì)觀測(cè)與認(rèn)知”(編號(hào):2013DFG21640) 中國科學(xué)院“百人計(jì)劃”項(xiàng)目“雷達(dá)遙感考古機(jī)理與方法示范研究”(編號(hào):Y5YR0300QM)共同資助
【分類號(hào)】:TN957.52
[Abstract]:Wolong Nature Reserve is one of the most important habitats for giant pandas. Combined with the advantages of radar remote sensing all day, all weather observation and the importance of forest cover to habitat evaluation, it is very important to study the precise mapping of forest with multi-phase and dual-polarization radar data. In this study, the radar data were first corrected by radiometric topography, and then five time-phase ALOS PALSAR data were selected, and the support vector machine (support vector machine,SVM) method was used for fine forest mapping. In this study, five multi-phase and two-polarization typical feature information were selected to participate in the initial training and classification. Then, HH_m,HV_m,TSD,HH_m-HV_m and HH_m/HV_m; obtained the optimal feature combination HH_m,HV_m,TSD,HH_m-HV_m. by the experiment and comparison of the classification accuracy of different information combinations. The accuracy of forest and non-forest users was 86.90% and 92.83% respectively, which was significantly better than that of single time and single polarization data (total classification accuracy was 55.47%). The results verify the validity of multi-temporal and dual-polarization radar remote sensing data in the fine forest mapping of natural heritage areas, and reveal the potential and application value of radar remote sensing in monitoring and evaluation of habitats in cloudy and rainy areas.
【作者單位】: 中國科學(xué)院遙感與數(shù)字地球研究所數(shù)字地球重點(diǎn)實(shí)驗(yàn)室;中國科學(xué)院大學(xué);聯(lián)合國教科文組織國際自然與文化遺產(chǎn)空間技術(shù)中心;山東科技大學(xué)測(cè)繪科學(xué)與工程學(xué)院;
【基金】:國家國際科技合作專項(xiàng)項(xiàng)目“全球變化對(duì)世界遺產(chǎn)影響空間精細(xì)觀測(cè)與認(rèn)知”(編號(hào):2013DFG21640) 中國科學(xué)院“百人計(jì)劃”項(xiàng)目“雷達(dá)遙感考古機(jī)理與方法示范研究”(編號(hào):Y5YR0300QM)共同資助
【分類號(hào)】:TN957.52
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 劉國梁;毫米波雙極化傳輸技術(shù)的研究[J];電信科學(xué);1988年06期
2 潘雪明,王澤美,焦永昌;一種槽耦合的雙頻雙極化微帶天*線[J];雷達(dá)科學(xué)與技術(shù);2005年04期
3 康雪姣;張金生;;一種雙頻雙極化3G天線的研究[J];微計(jì)算機(jī)信息;2008年32期
4 金擰民;;利用煇卡,
本文編號(hào):2217731
本文鏈接:http://sikaile.net/kejilunwen/xinxigongchenglunwen/2217731.html
最近更新
教材專著