全極化SAR地物分類與極化方位角補(bǔ)償
發(fā)布時(shí)間：2018-11-27 09:23
【摘要】：全極化合成孔徑雷達(dá)（Synthetic Aperture Radar，，SAR）作為一種先進(jìn)的遙感信息獲取手段，更加完整的記錄了目標(biāo)的回波散射信息。全極化SAR分類結(jié)果既可為目標(biāo)檢測(cè)、邊緣提取等進(jìn)一步的分析或解譯提供輔助信息,也可作為最終結(jié)果。與普通遙感圖像相比，全極化SAR分類技術(shù)對(duì)于揭示地物極化散射信息更具有研究?jī)r(jià)值。 本文以提高全極化SAR數(shù)據(jù)的分類精度為主要目的,研究了全極化SAR圖像分類方法。 目前使用全極化SAR進(jìn)行地物分類的方法主要有兩種：非監(jiān)督分類和監(jiān)督分類。大部分非監(jiān)督分類方法的優(yōu)點(diǎn)在于提供了用于指派最終地物類型的輔助信息；但每個(gè)聚類對(duì)應(yīng)某種單一散射機(jī)制，并不能代表實(shí)際地物，因此在對(duì)大規(guī)模的遙感數(shù)據(jù)處理時(shí)必須依靠人工專家的參與解譯。監(jiān)督分類方法通�；谙袼鼗蛐^(qū)域得到底層特征，利用這些底層特征對(duì)具有單一散射機(jī)制的地物進(jìn)行分類非常有效，但對(duì)復(fù)雜地物進(jìn)行分類時(shí)會(huì)遇到困難。針對(duì)上述兩種問題，本文提出一種使用中間層特征MLF(Middle-Level-Feature)的監(jiān)督分類方法。即統(tǒng)計(jì)以某像素為中心的一定區(qū)域（矩形窗口）內(nèi)各“中間成分（基于底層極化特征得到的非監(jiān)督聚類類別）”的占比作為該像素的MLF，依此計(jì)算所有位置像素的MLF，然后利用支持向量機(jī)進(jìn)行監(jiān)督分類。本文在覆蓋武漢地區(qū)的Radarsat-2全極化數(shù)據(jù)上，與基于經(jīng)典全極化特征的SVM（Support Vector Machine）監(jiān)督分類方法進(jìn)行了對(duì)比，研究了不同中間成分獲取方法以及特征支持窗口對(duì)于分類性能的影響，結(jié)果顯示本文方法有很好的性能并有進(jìn)一步提升的空間。 對(duì)于全極化SAR數(shù)據(jù)中眾多的極化信息，極化方位角反映了散射目標(biāo)相對(duì)于雷達(dá)視線的旋轉(zhuǎn)角度，即方位向坡度。在極化SAR圖像分類中，同一類別地物目標(biāo)所處方位向坡度的差異，體現(xiàn)在極化SAR數(shù)據(jù)中是極化特性的不同，將導(dǎo)致被分為不同的類別。為了消除這種由于地形因素造成的分類誤差，本文進(jìn)行了極化方位角的補(bǔ)償，以改善極化SAR數(shù)據(jù)的分類結(jié)果。 本文利用DEM（Digital Elevation Model）估計(jì)出極化方位角并做了極化方位角補(bǔ)償。實(shí)驗(yàn)發(fā)現(xiàn)，極化方位角補(bǔ)償后，經(jīng)過極化補(bǔ)償之后，F(xiàn)reeman分解中體散射功率會(huì)減小、二次散射功率均減小、絕大多數(shù)像素的面散射分量也會(huì)減小，但是減小值大部分都在0附近。對(duì)于Cloude分解，極化方位角補(bǔ)償后，極化數(shù)據(jù)區(qū)分兩個(gè)相對(duì)較弱的散射分量的能力增強(qiáng)，同時(shí)散射介質(zhì)的隨機(jī)性增強(qiáng)，代表散射過程物理機(jī)制的alpha值約60%的像素值減小。
[Abstract]:Fully polarized synthetic aperture radar (Synthetic Aperture Radar,SAR) as an advanced remote sensing information acquisition method, more complete recording of the target echo scattering information. The results of fully polarized SAR classification can not only provide auxiliary information for further analysis or interpretation, such as target detection, edge extraction and so on, but also can be used as final results. Compared with conventional remote sensing images, the fully polarized SAR classification technique is more valuable to reveal the polarimetric scattering information of ground objects. In order to improve the classification accuracy of fully polarized SAR data, a method of full polarization SAR image classification is studied in this paper. At present, there are two main methods for ground object classification using fully polarized SAR: unsupervised classification and supervised classification. The advantage of most unsupervised classification methods is that they provide auxiliary information for assigning final feature types. However, each cluster corresponds to a single scattering mechanism, which can not represent the real objects. Therefore, the interpretation of large-scale remote sensing data must rely on the participation of artificial experts. Supervised classification methods are usually based on pixels or small regions to obtain bottom features. Using these underlying features to classify objects with a single scattering mechanism is very effective, but it will be difficult to classify complex objects. In order to solve the above two problems, a supervised classification method using MLF (Middle-Level-Feature) is proposed. That is, the percentage of the "intermediate components (unsupervised clustering categories based on the underlying polarization feature) in a certain region (rectangular window) centered on a pixel is counted as the MLF, of the pixel. The MLF, of all the pixels is calculated accordingly." Then support vector machine is used for supervised classification. In this paper, the Radarsat-2 full polarization data covering Wuhan area are compared with the SVM (Support Vector Machine) supervised classification method based on classical full polarization features. The effects of different intermediate component acquisition methods and feature support windows on classification performance are studied. The results show that the proposed method has good performance and further improvement. For all polarimetric SAR data, the polarization azimuth reflects the rotation angle of the scattering target relative to the radar line of sight, that is, the azimuth slope. In the classification of polarimetric SAR images, the difference of azimuth gradient of the same ground object is reflected in the polarization characteristics of the polarimetric SAR data, which will lead to the classification of different categories. In order to eliminate the classification error caused by topographic factors, the polarization azimuth compensation is carried out to improve the classification results of polarized SAR data. In this paper, the polarization azimuth angle is estimated by DEM (Digital Elevation Model) and the polarization azimuth compensation is made. The experimental results show that after polarization compensation and polarization compensation, the volume scattering power and secondary scattering power in Freeman decomposition will decrease, and the surface scattering components of most pixels will also decrease, but most of the decreases are near zero. For Cloude decomposition, after polarization azimuth compensation, the ability of polarization data to distinguish two relatively weak scattering components is enhanced, and the randomness of scattering medium is enhanced, and the pixel value of alpha representing the physical mechanism of scattering process is reduced by about 60%.
【學(xué)位授予單位】：貴州師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN957.52
本文編號(hào)：2360208
[Abstract]:Fully polarized synthetic aperture radar (Synthetic Aperture Radar,SAR) as an advanced remote sensing information acquisition method, more complete recording of the target echo scattering information. The results of fully polarized SAR classification can not only provide auxiliary information for further analysis or interpretation, such as target detection, edge extraction and so on, but also can be used as final results. Compared with conventional remote sensing images, the fully polarized SAR classification technique is more valuable to reveal the polarimetric scattering information of ground objects. In order to improve the classification accuracy of fully polarized SAR data, a method of full polarization SAR image classification is studied in this paper. At present, there are two main methods for ground object classification using fully polarized SAR: unsupervised classification and supervised classification. The advantage of most unsupervised classification methods is that they provide auxiliary information for assigning final feature types. However, each cluster corresponds to a single scattering mechanism, which can not represent the real objects. Therefore, the interpretation of large-scale remote sensing data must rely on the participation of artificial experts. Supervised classification methods are usually based on pixels or small regions to obtain bottom features. Using these underlying features to classify objects with a single scattering mechanism is very effective, but it will be difficult to classify complex objects. In order to solve the above two problems, a supervised classification method using MLF (Middle-Level-Feature) is proposed. That is, the percentage of the "intermediate components (unsupervised clustering categories based on the underlying polarization feature) in a certain region (rectangular window) centered on a pixel is counted as the MLF, of the pixel. The MLF, of all the pixels is calculated accordingly." Then support vector machine is used for supervised classification. In this paper, the Radarsat-2 full polarization data covering Wuhan area are compared with the SVM (Support Vector Machine) supervised classification method based on classical full polarization features. The effects of different intermediate component acquisition methods and feature support windows on classification performance are studied. The results show that the proposed method has good performance and further improvement. For all polarimetric SAR data, the polarization azimuth reflects the rotation angle of the scattering target relative to the radar line of sight, that is, the azimuth slope. In the classification of polarimetric SAR images, the difference of azimuth gradient of the same ground object is reflected in the polarization characteristics of the polarimetric SAR data, which will lead to the classification of different categories. In order to eliminate the classification error caused by topographic factors, the polarization azimuth compensation is carried out to improve the classification results of polarized SAR data. In this paper, the polarization azimuth angle is estimated by DEM (Digital Elevation Model) and the polarization azimuth compensation is made. The experimental results show that after polarization compensation and polarization compensation, the volume scattering power and secondary scattering power in Freeman decomposition will decrease, and the surface scattering components of most pixels will also decrease, but most of the decreases are near zero. For Cloude decomposition, after polarization azimuth compensation, the ability of polarization data to distinguish two relatively weak scattering components is enhanced, and the randomness of scattering medium is enhanced, and the pixel value of alpha representing the physical mechanism of scattering process is reduced by about 60%.
【學(xué)位授予單位】：貴州師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN957.52
【參考文獻(xiàn)】
相關(guān)期刊論文 前6條
1 干江濤;徐豐;;基于SAR成像的復(fù)雜環(huán)境中目標(biāo)識(shí)別[J];復(fù)旦學(xué)報(bào)(自然科學(xué)版);2006年01期
2 葛之江;張潤(rùn)寧;朱麗;;國(guó)外星載SAR系統(tǒng)的最新進(jìn)展[J];航天器工程;2008年06期
3 金亞秋,羅霖;用合成孔徑雷達(dá)(SAR)單次飛行全極化圖像數(shù)據(jù)進(jìn)行地面數(shù)字高程(DEM)反演[J];中國(guó)科學(xué)E輯:信息科學(xué);2004年06期
4 梁淮寧,王建國(guó),黃順吉;全極化合成孔徑雷達(dá)(SAR)高度信息檢測(cè)技術(shù)[J];信號(hào)處理;2001年02期
5 陳曦;張紅;王超;;由地形坡度引起的極化方位角偏移的估計(jì)[J];遙感技術(shù)與應(yīng)用;2007年01期
6 尤紅建;丁赤飚;吳一戎;;基于DEM的星載SAR圖像模擬以及用于圖像精校正[J];中國(guó)空間科學(xué)技術(shù);2006年01期
相關(guān)博士學(xué)位論文 前2條
1 夏偉杰;合成孔徑雷達(dá)回波仿真與圖像模擬[D];南京航空航天大學(xué);2010年
2 吳永輝;極化SAR圖像分類技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2007年
本文編號(hào)：2360208
本文鏈接：http://sikaile.net/kejilunwen/wltx/2360208.html
最近更新
教材專著
