本文關(guān)鍵詞：基于多層網(wǎng)絡(luò)模型的全極化SAR圖像分類　出處：《武漢大學(xué)》2015年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 全極化合成子孔徑雷達(dá) 分類 多層網(wǎng)絡(luò)模型 深度學(xué)習(xí) 遷移學(xué)習(xí)

【摘要】：全極化合成孔徑雷達(dá)(Polarimetric Synthetic Aperture Radar, PolSAR)是一種先進(jìn)的對(duì)地測(cè)量系統(tǒng),能同時(shí)獲取4個(gè)極化通道的SAR圖像。因此,通過全極化SAR圖像可以獲得豐富的地物信息。圖像分類是極化SAR系統(tǒng)的一個(gè)重要研究?jī)?nèi)容,在農(nóng)林業(yè)規(guī)劃、環(huán)境保護(hù)等領(lǐng)域都有著廣泛的應(yīng)用,開展全極化SAR圖像分類研究對(duì)于提高SAR遙感的應(yīng)用水平具有重要的理論意義及實(shí)用價(jià)值。近年來,在光學(xué)領(lǐng)域圖像分類算法發(fā)展迅速,出現(xiàn)了很多新的模型或概念,如詞袋模型,空間金字塔、稀疏編碼,特征表達(dá)等,從事全極化SAR圖像分類的研究人員紛紛借鑒光學(xué)圖像分類中的優(yōu)秀算法和概念,針對(duì)全極化SAR圖像提出了很多新的的特征表達(dá)和特征編碼方法,且取得了較好的成績(jī)。2006年,Hinton等人在光學(xué)領(lǐng)域首次提出了深度學(xué)習(xí)的概念,開啟了特征學(xué)習(xí)的研究,它能通過構(gòu)建多層網(wǎng)絡(luò)模型自動(dòng)的從原始圖像中學(xué)習(xí)出更本質(zhì)的特征,從而有利于分類研究。此后,深度學(xué)習(xí)的相關(guān)研究如火如荼,在光學(xué)圖像分類領(lǐng)域更是創(chuàng)造了諸多奇跡。本文引入深度學(xué)習(xí)的思想進(jìn)而實(shí)現(xiàn)全極化SAR圖像的分類,但極化SAR圖像不同于光學(xué)圖像,不能將光學(xué)圖像中的深度學(xué)習(xí)模型直接用于全極化SAR圖像分類,主要存在如下幾個(gè)方面的問題：(1) SAR圖像與光學(xué)圖像在成像方式上有很大不同,光學(xué)圖像是通過可見光傳感器成像,可以獲得地物的灰度信息,而SAR是通過微波傳感器成像,然后以二進(jìn)制復(fù)數(shù)形式記錄地物的回波信息；另外,SAR圖像所固有的相干斑噪聲十分嚴(yán)重,信噪比極低,大部分信息都被淹沒在相干斑噪聲里,嚴(yán)重影響了全極化SAR圖像解譯及后續(xù)的應(yīng)用,因此PolSAR數(shù)據(jù)需要處理后才能利用深度學(xué)習(xí)模型進(jìn)行分類；(2) 全極化SAR能同時(shí)獲取4個(gè)不同通道的SAR圖像,在互易媒質(zhì)的后向散射情況下,同一地物也對(duì)應(yīng)著3幅單極化SAR圖像,而原有的深度學(xué)習(xí)模型都是建立在單通道數(shù)據(jù)上的,不能充分的利用全極化SAR圖像豐富的地物信息；(3) 深度學(xué)習(xí)往往需要大量數(shù)據(jù)對(duì)多層網(wǎng)絡(luò)模型進(jìn)行訓(xùn)練,而目標(biāo)全極化SAR圖像往往沒有足夠的數(shù)據(jù)來訓(xùn)練多層網(wǎng)絡(luò)模型。為了充分利用深度學(xué)習(xí)的優(yōu)勢(shì)進(jìn)行全極化SAR圖像分類,就需要在深度學(xué)習(xí)和極化SAR圖像之間構(gòu)建一座橋梁,同時(shí)需要構(gòu)建適合全極化SAR圖像的多層網(wǎng)絡(luò)模型用于特征學(xué)習(xí)和分類。本文從極化SAR基礎(chǔ)理論出發(fā),在描述極化SAR統(tǒng)計(jì)分布模型和極化分解等原理的基礎(chǔ)上引入了深度學(xué)習(xí),為了解決深度學(xué)習(xí)引入全極化SAR圖像過程中遇到的一些問題,本文主要做了3個(gè)方面的工作：(1) 考慮到SAR圖像的成像機(jī)理不同于光學(xué)圖像,深度學(xué)習(xí)往往不能直接用于極化SAR圖像分類,本文構(gòu)建了一個(gè)基于統(tǒng)計(jì)分布的網(wǎng)絡(luò)結(jié)構(gòu)單元,以在深度學(xué)習(xí)和全極化SAR圖像之間構(gòu)建一座橋梁；(2) 為了充分地利用全極化SAR所包含的豐富地物信息,本文從特征融合和特征學(xué)習(xí)兩個(gè)不同的角度構(gòu)建了兩個(gè)多層網(wǎng)絡(luò)模型用于特征提取和分類。第1個(gè)多層網(wǎng)絡(luò)融合了多種類型的特征,采用字典學(xué)習(xí)實(shí)現(xiàn)了空間金字塔特征表達(dá),并構(gòu)建了一個(gè)雙層SVM實(shí)現(xiàn)了全極化SAR圖像的分類。第2個(gè)多層網(wǎng)絡(luò)是對(duì)多層反卷積網(wǎng)絡(luò)進(jìn)行了改進(jìn),構(gòu)建了一個(gè)適合全極化SAR圖像分類的多層反卷積網(wǎng)絡(luò),同時(shí)在反卷積網(wǎng)絡(luò)中引入了一種新的軟概率池化方法;(3) 考慮到目標(biāo)極化SAR沒有足夠的數(shù)據(jù)用于多層網(wǎng)絡(luò)的訓(xùn)練,本文引入了遷移學(xué)習(xí)的方法,采用相似的極化SAR數(shù)據(jù)對(duì)多層網(wǎng)絡(luò)進(jìn)行訓(xùn)練,將多層網(wǎng)絡(luò)學(xué)習(xí)的特征作為中層表達(dá),再用目標(biāo)極化SAR圖像對(duì)中層表達(dá)遷移學(xué)習(xí),以能對(duì)目標(biāo)極化SAR數(shù)據(jù)進(jìn)行更準(zhǔn)確的分類。論文在解決上述理論和技術(shù)問題的基礎(chǔ)上,利用多個(gè)多層網(wǎng)絡(luò)模型對(duì)全極化SAR圖像進(jìn)行了分類研究,在中國(guó)電子集團(tuán)第三十八研究所獲取的X波段單航跡海南省陵水縣全極化SAR數(shù)據(jù)上進(jìn)行了實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明多層網(wǎng)絡(luò)模型在全極化SAR圖像分類領(lǐng)域確實(shí)具有很大的潛力。
[Abstract]:Polarimetric synthetic aperture radar (Polarimetric Synthetic Aperture Radar, PolSAR) is a kind of advanced measurement system, SAR image is able to obtain the 4 polarization channels. Therefore, by fully polarimetric SAR images can provide abundant information. Image classification is an important research content of polarimetric SAR system, in agriculture and forestry planning, environmental protection and other fields have a wide range of applications, to carry out the classification of polarimetric SAR images has important theoretical significance and practical value to improve the application level of SAR remote sensing. In recent years, the development in the field of optical image classification algorithm rapidly, there are many models or new concepts, such as the bag of words model, space in Pyramid sparse encoding, feature, expression, researchers engaged in polarimetric SAR image classification algorithm and the concept of reference have excellent optical image classification, based on the full polarization SAR images are proposed. A lot of new feature expression and feature encoding method, and achieved good results in.2006, Hinton et al first proposed the concept of deep learning in the field of optics, the study on characteristics of learning, it can through the construction of automatic learning out of the essential characteristics of the original image from the secondary multi-layer model so as to facilitate the classification study. Since then, the related research of deep learning in optical image classification field like a raging fire, but also created many miracles. This paper introduces the idea of deep learning so as to realize the classification of polarimetric SAR images, but the polarization SAR image is different from optical image, can not be deep learning model in the optical image directly for polarimetric SAR image classification. Mainly has the following several aspects: (1) SAR and optical images are very different in the imaging mode, the optical image is visible through the sensor imaging, can In order to obtain the gray information of objects, while the SAR is through the microwave imaging sensor, and then to echo information of plural recording binary objects; in addition, coherence inherent speckle noise in SAR images is very serious, the signal-to-noise ratio is very low, most of the information that is submerged in the speckle noise, seriously affecting the polarization SAR image solution translation and subsequent application, so PolSAR data needs to be processed before the use of deep learning model classification; (2) fully polarimetric SAR can obtain 4 different channels of SAR image at the same time, the reciprocal medium backscatter case, the same object is corresponding with 3 single polarization SAR images, and the original depth learning models are based on single channel data, feature information of fully polarimetric SAR image can't take advantage of the rich; (3) deep learning often need training on multilayer network model for large amounts of data, and the goal of all Polarimetric SAR images often do not have enough data to train the multilayer network model. In order to make full use of deep learning the advantages of fully polarimetric SAR image classification, we need to build a bridge between deep learning and polarization SAR image, also need to build features for learning and classification of multilayer network model for fully polarimetric SAR images. This paper from the polarization SAR the basic theory, the deep learning is introduced based on SAR statistical distribution model to describe the polarization and polarization decomposition principle, in order to solve some problems encountered in deep learning into full polarimetric SAR image process, this paper has 3 aspects: (1) considering the imaging mechanism of SAR image of Yu Guangxue deep learning image, often can not be directly used for classification of polarimetric SAR images, this paper constructs a network structure based on the statistical distribution of the unit, in the depth of learning and Build a bridge between fully polarimetric SAR image; (2) in order to enrich the feature information of full use of polarimetric SAR contains, the feature fusion and feature learning from two different angles constructed two multilayer network model for feature extraction and classification. The first characteristics of various types of multi network fusion, using dictionary learning can express the space characteristic of Pyramid, and the construction of a double SVM to achieve the classification of fully polarimetric SAR image. Second multilayer network is of multilayer deconvolutional networks is improved, construct a suitable polarimetric SAR image deconvolution multilayer network classification, and introduces a new soft probability pool in the method of deconvolution in the network; (3) taking into account the target SAR does not have enough data for training multilayer network, this paper introduces a method of transfer learning, using polarimetric SAR data of similar Multilayer neural network training, will feature multilayer network learning as the middle expression, then the target polarimetric SAR image transfer learning of middle expression, to carry out a more accurate classification of polarimetric SAR data. Based on the theory and technology to solve the above problems, the use of multiple multilayer network model classification research on full polarization SAR images acquired in the study of thirty-eighth China Electronics Group X band single track in Lingshui County of Hainan province fully polarimetric SAR data for the experiment results show that it has great potential in the field of multilayer network model of fully polarimetric SAR image.

【學(xué)位授予單位】：武漢大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：P237

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 金亞秋,曾亮;一層非均勻隨機(jī)取向非球形粒子的全極化散射[J];電子學(xué)報(bào);1992年09期

2 王新彪;李靖;姜景山;;相關(guān)型全極化輻射計(jì)研究[J];遙感技術(shù)與應(yīng)用;2008年05期

3 王雪松;常宇亮;李永禎;戴幻堯;何密;肖順平;;極化雷達(dá)的同時(shí)全極化測(cè)量與校準(zhǔn)技術(shù)[J];科技導(dǎo)報(bào);2011年26期

4 王勤誠(chéng);復(fù)合型鐵氧體全極化器[J];寧波大學(xué)學(xué)報(bào)(理工版);2003年03期

5 李麗麗;馬國(guó)慶;;全極化探地雷達(dá)采集系統(tǒng)及校準(zhǔn)技術(shù)[J];地球物理學(xué)進(jìn)展;2011年06期

6 陸浩;王振占;劉t熲，

本文編號(hào)：1418315