本文選題：PolSAR + 集成學(xué)習(xí)　； 參考：《西安電子科技大學(xué)》2014年碩士論文

【摘要】：極化合成孔徑雷達(dá)(Polarimetric Synthetic Aperture Radar,PolSAR)是一種多參數(shù)、多通道的成像雷達(dá)系統(tǒng),因其全天時(shí),全天候,高分辨的優(yōu)勢(shì)而得到廣泛的應(yīng)用�；跈C(jī)器學(xué)習(xí)的PolSAR圖像分類方法取得了很高的分類精度,但是當(dāng)有標(biāo)簽噪聲存在時(shí),分類結(jié)果會(huì)受到很大的影響。本文基于集成學(xué)習(xí),針對(duì)PolSAR圖像分類中標(biāo)簽噪聲的問(wèn)題,進(jìn)行了深入的研究,主要包括以下三方面的內(nèi)容:1.結(jié)合PolSAR圖像的偏振參數(shù)、散射、紋理特征,提出了一種基于AdaBoost的PolSAR圖像監(jiān)督分類算法(Knn.Ada Boost)。此方法利用PolSAR圖像的偏振參數(shù)、極化散射特征和圖像的紋理特征,作為Ada Boost的輸入特征,Knn.Ada Boost算法預(yù)先通過(guò)K nn計(jì)算PolSAR圖像中每個(gè)像素的抗噪因子,根據(jù)抗噪因子修改Ada Boost算法中的樣本權(quán)值更新策略。實(shí)驗(yàn)采用了一組模擬PolSAR數(shù)據(jù)和五組真實(shí)PolSAR數(shù)據(jù),實(shí)驗(yàn)結(jié)果表明,K nn.Ada Boost算法提高了AdaBoost的分類精度,具有很好的抗噪性能。2.在Knn.Ada Boost的工作基礎(chǔ)上,提出了一種基于Ada Boost的PolSAR圖像半監(jiān)督分類算法(Semi.Knn.AdaBoost)。在Knn.Ada Boost的框架下,引入Wishart距離度量,在每一次迭代結(jié)束時(shí),根據(jù)有標(biāo)記樣本計(jì)算獲得Wishart聚類中心,從預(yù)測(cè)標(biāo)記中選擇距離Wishart聚類中心最近的若干個(gè)樣本,分別加入對(duì)應(yīng)的類別進(jìn)入下一次迭代。實(shí)驗(yàn)采用一組模擬PolSAR數(shù)據(jù)和五組真實(shí)PolSAR數(shù)據(jù),結(jié)果表明,Semi.Knn.Ada Boost豐富了訓(xùn)練樣本,分類正確率有一定的提升。3.在PolSAR圖像分類問(wèn)題中,提出了一種基于集成學(xué)習(xí)的標(biāo)簽噪聲水平預(yù)測(cè)方法EEL(Estimated by Ensemble Learning)。采用PolSAR圖像的相干矩陣中九個(gè)元素作為特征,利用不同的分類算法,學(xué)習(xí)得到相互獨(dú)立的分類器,用這些分類器分別對(duì)標(biāo)記樣本分類,然后用多數(shù)投票和全投票的策略判定一個(gè)已標(biāo)記樣本是否是噪聲,多數(shù)投票策略即對(duì)一個(gè)樣本的預(yù)測(cè),如果超過(guò)半數(shù)分類器的分類結(jié)果是相同的,則認(rèn)為這個(gè)已標(biāo)記樣本不是噪聲,否則是噪聲;全投票策略只認(rèn)定所有分類器投票結(jié)果相同時(shí),此樣本才不是噪聲,否則是噪聲。實(shí)驗(yàn)采用三組UCI數(shù)據(jù)和四組模擬的PolSAR數(shù)據(jù),結(jié)果表明,在標(biāo)簽噪聲水平比較低時(shí),此方法能夠正確的預(yù)測(cè),而標(biāo)簽噪聲水平比較高時(shí),預(yù)測(cè)出的標(biāo)簽噪聲水平則不是很準(zhǔn)確。本文工作得到了國(guó)家自然科學(xué)基金(No.61173092)、新世紀(jì)優(yōu)秀人才支持計(jì)劃(No.66ZY110)和陜西省科學(xué)技術(shù)研究發(fā)展計(jì)劃項(xiàng)目(No.2013KJXX-64)資助。
[Abstract]:Polarimetric Synthetic Aperture Radarr (PolSAR) is a multi-parameter, multi-channel imaging radar system, which is widely used because of its advantages of all-weather, all-weather and high-resolution.The PolSAR image classification method based on machine learning has achieved high classification accuracy, but when there is label noise, the classification results will be greatly affected.Based on ensemble learning, this paper focuses on the problem of label noise in PolSAR image classification, including the following three aspects: 1.Based on the polarization parameters, scattering and texture features of PolSAR images, a supervised classification algorithm for PolSAR images based on AdaBoost is proposed.Using polarization parameters, polarization scattering features and texture features of PolSAR images, the Knn.Ada Boost algorithm is used as the input feature of Ada Boost to calculate the anti-noise factor of each pixel in PolSAR image.The sample weight updating strategy in Ada Boost algorithm is modified according to the anti-noise factor.A set of simulated PolSAR data and five groups of real PolSAR data are used in the experiment. The experimental results show that the K nn.Ada Boost algorithm improves the classification accuracy of AdaBoost and has a good anti-noise performance.Based on the work of Knn.Ada Boost, a semi-supervised PolSAR image classification algorithm based on Ada Boost is proposed.In the framework of Knn.Ada Boost, the Wishart distance metric is introduced. At the end of each iteration, the Wishart cluster center is obtained according to the calculation of labeled samples, and several samples closest to the Wishart cluster center are selected from the prediction markers.Add corresponding categories to the next iteration.A set of simulated PolSAR data and five groups of real PolSAR data are used in the experiment. The results show that Semi.Knn.Ada Boost enriches the training samples and improves the classification accuracy. 3.In the problem of PolSAR image classification, an ensemble learning based label noise prediction method, EEL(Estimated by Ensemble learning, is proposed.Using nine elements in the coherent matrix of PolSAR image as features and using different classification algorithms, independent classifiers are obtained, and these classifiers are used to classify the labeled samples respectively.Then the majority voting strategy is used to determine whether a marked sample is noisy or not, and the majority voting strategy is the prediction of a sample, if the classification results of more than half of the classifiers are the same.It is considered that the labeled sample is not noise, otherwise it is noise; if the voting result of all classifiers is the same, the sample is not noise, otherwise it is noise.Three groups of UCI data and four groups of simulated PolSAR data are used in the experiment. The results show that this method can correctly predict the label noise level when the label noise level is low, but the predicted label noise level is not very accurate when the label noise level is high.This work is supported by the National Natural Science Foundation No. 61173092, the New Century Talent support Program No. 66ZY110) and the Shaanxi Provincial Science and Technology Research and Development Program Project No. 2013KJXX-64).
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN957.52

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 代大海;王雪松;肖順平;李永禎;;PolSAR有源假目標(biāo)干擾的鑒別與對(duì)消[J];電子學(xué)報(bào);2007年09期

2 李洪忠;陳勁松;王超;張紅;;基于相似性的POLSAR占優(yōu)散射歸類及非監(jiān)督聚類[J];電子與信息學(xué)報(bào);2012年06期

3 ;[J];;年期

相關(guān)碩士學(xué)位論文 前2條

1 陳國(guó)棟;基于集成學(xué)習(xí)的PolSAR標(biāo)簽噪聲研究[D];西安電子科技大學(xué);2014年

2 楊丹;POLSAR原始回波信號(hào)仿真研究[D];哈爾濱工業(yè)大學(xué);2007年

，

本文編號(hào)：1740480