【摘要】：合成孔徑雷達(dá)(Synthetic Aperture Radar,SAR)具有廣闊的研究和應(yīng)用前景,其被廣泛地應(yīng)用于包含地質(zhì)勘測(cè)、地形測(cè)繪和制圖、海洋應(yīng)用在內(nèi)的民用領(lǐng)域。而在軍事領(lǐng)域中,SAR可用作全天時(shí)全天候全球戰(zhàn)略偵察與重點(diǎn)戰(zhàn)區(qū)軍事監(jiān)控。SAR目標(biāo)識(shí)別的研究主要依賴(lài)于大規(guī)模的帶標(biāo)簽數(shù)據(jù)樣本,然而,要獲得大量的樣本數(shù)據(jù)及其正確的分類(lèi)標(biāo)簽,需要耗費(fèi)非常大的人力物力資源。不僅如此,基于龐大數(shù)據(jù)訓(xùn)練分類(lèi)器同樣耗費(fèi)大量資源并且難度較高。因此,如何在保證識(shí)別性能的前提下降低資源開(kāi)銷(xiāo)成為了一個(gè)新的熱點(diǎn)研究方向。通過(guò)較少訓(xùn)練樣本得到的分類(lèi)器性能不夠成熟,因此SAR圖像數(shù)量的稀少,是制約SAR圖像目標(biāo)識(shí)別發(fā)展的主要原因之一。然而,SAR圖像樣本數(shù)量將隨著時(shí)間的推移不斷增長(zhǎng),同時(shí),又希望能夠直接利用新增的SAR圖像提升原有分類(lèi)器性能,而不需要與原有的圖形樣本混合重新訓(xùn)練新分類(lèi)器,以此達(dá)到減小訓(xùn)練開(kāi)支的目的.將利用不斷新增的樣本在已有的分類(lèi)器基礎(chǔ)上,迭代訓(xùn)練以提升分類(lèi)器性能的方法定義為更新學(xué)習(xí)機(jī)制。本文研究主要針對(duì)于SAR圖像目標(biāo)識(shí)別問(wèn)題,研究基于卷積神經(jīng)網(wǎng)絡(luò)的SAR圖像特征提取方法,并建立一種基于更新學(xué)習(xí)機(jī)制的SAR圖像目標(biāo)識(shí)別方法。本文的主要內(nèi)容分為以下部分:1、介紹SAR圖像目標(biāo)識(shí)別的背景,分析該課題的研究意義,以及國(guó)內(nèi)外學(xué)者在SAR圖像目標(biāo)識(shí)別領(lǐng)域所做的主要研究;2、分析SAR圖像特性及其特征提取方法,引入機(jī)器學(xué)習(xí)理論于MSTAR數(shù)據(jù)庫(kù);3、實(shí)現(xiàn)基于支持向量機(jī)的SAR圖像目標(biāo)識(shí)別方法,并重點(diǎn)介紹深度學(xué)習(xí)在目標(biāo)識(shí)別領(lǐng)域的應(yīng)用,利用深度學(xué)習(xí)中的卷積神經(jīng)網(wǎng)絡(luò)理論實(shí)現(xiàn)SAR圖像目標(biāo)識(shí)別,并與其他方法進(jìn)行對(duì)比;4、以卷積神經(jīng)網(wǎng)絡(luò)為主,支持向量機(jī)為輔助分類(lèi)器實(shí)現(xiàn)基于卷積神經(jīng)網(wǎng)絡(luò)與SVM的更新學(xué)習(xí)機(jī)制。
[Abstract]:Synthetic Aperture Radar (Synthetic Aperture Radar,SAR) has a wide range of research and application prospects. It has been widely used in civil fields, including geological survey, topographic mapping and mapping, and marine applications. In the military field, SAR can be used as global strategic reconnaissance and military surveillance in all-weather and all-weather. The research of target recognition mainly depends on large-scale labeled data samples, however, the research of target recognition is based on large-scale labeled data samples. In order to obtain a large amount of sample data and correct classification label, it takes a lot of human and material resources. Moreover, training classifiers based on huge data also costs a lot of resources and is difficult. Therefore, how to reduce resource overhead under the premise of ensuring recognition performance has become a new hot research direction. The performance of classifier obtained by fewer training samples is not mature enough, so the scarcity of SAR images is one of the main reasons restricting the development of SAR image target recognition. However, the number of SAR image samples will continue to increase with the passage of time. At the same time, it is hoped that the performance of the existing classifier can be improved directly by using the new SAR image, without the need to re-train the new classifier with the existing graphics samples. In order to achieve the purpose of reducing the cost of training. The updated learning mechanism is defined as the method of iterative training to improve the performance of classifiers based on the existing classifiers. This paper focuses on the problem of target recognition for SAR images, studies the feature extraction method of SAR images based on convolution neural network, and establishes a SAR image target recognition method based on update learning mechanism. The main contents of this paper are as follows: 1. The background of SAR image target recognition is introduced, and the research significance of this subject is analyzed, as well as the main research done by domestic and foreign scholars in the field of SAR image target recognition; 2. The characteristics of SAR image and its feature extraction methods are analyzed, and the machine learning theory is introduced into the MSTAR database. 3, the method of SAR image target recognition based on support vector machine is realized, and the application of depth learning in target recognition field is introduced emphatically. The convolutional neural network theory of depth learning is used to realize SAR image target recognition. And compared with other methods; 4, based on convolution neural network and support vector machine as assistant classifier, the updating learning mechanism based on convolution neural network and SVM is realized.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TN957.52

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 王平;紀(jì)鋼;;基于逼近增強(qiáng)算子的合成孔徑雷達(dá)圖像特征提取算法[J];計(jì)算機(jī)應(yīng)用研究;2015年07期

2 鄭胤;陳權(quán)崎;章毓晉;;深度學(xué)習(xí)及其在目標(biāo)和行為識(shí)別中的新進(jìn)展[J];中國(guó)圖象圖形學(xué)報(bào);2014年02期

3 韓萍;王歡;;結(jié)合KPCA和稀疏表示的SAR目標(biāo)識(shí)別方法研究[J];信號(hào)處理;2013年12期

4 周漢飛;李禹;粟毅;;基于壓縮感知的多角度SAR特征提取[J];電子學(xué)報(bào);2013年03期

5 孫志軍;薛磊;許陽(yáng)明;王正;;深度學(xué)習(xí)研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2012年08期

6 胡利平;劉宏偉;尹奎英;吳順君;;兩向二維最大子類(lèi)散度差鑒別分析及其在SAR目標(biāo)識(shí)別中的應(yīng)用[J];航空學(xué)報(bào);2009年12期

7 胡利平;劉宏偉;吳順君;;一種新的SAR圖像目標(biāo)識(shí)別預(yù)處理方法[J];西安電子科技大學(xué)學(xué)報(bào);2007年05期

8 韓萍,吳仁彪,王兆華,王蘊(yùn)紅;基于KPCA準(zhǔn)則的SAR目標(biāo)特征提取與識(shí)別[J];電子與信息學(xué)報(bào);2003年10期

相關(guān)碩士學(xué)位論文 前1條

1 高貴;高分辨率SAR圖像目標(biāo)特征提取研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2003年

，

本文編號(hào)：2468799