基于自適應(yīng)頻域信息和深度學(xué)習(xí)的SAR圖像分割
發(fā)布時(shí)間：2019-05-24 20:01
【摘要】：SAR圖像包含多種地物信息,已經(jīng)被廣泛應(yīng)用在目標(biāo)識(shí)別、災(zāi)害評(píng)估、環(huán)境監(jiān)測(cè)與跟蹤等民用領(lǐng)域和軍用領(lǐng)域,圖像中各類(lèi)目標(biāo)的準(zhǔn)確分割,對(duì)SAR圖像后續(xù)的處理有重要的意義。SAR具有全時(shí)段、全天候的優(yōu)勢(shì),但由于數(shù)據(jù)量龐大、圖像地物目標(biāo)豐富、受相干斑噪聲污染嚴(yán)重等特點(diǎn),高分辨SAR圖像的處理面臨著眾多挑戰(zhàn)。因此,SAR圖像分割一直是SAR信息處理應(yīng)用領(lǐng)域的熱門(mén)研究?jī)?nèi)容之一。在研究目前SAR圖像分割發(fā)展情況的基礎(chǔ)上,本文考慮高分辨SAR圖像的特點(diǎn),結(jié)合自適應(yīng)頻域信息和深度學(xué)習(xí)理論進(jìn)行SAR圖像分割的研究,主要研究?jī)?nèi)容如下:1.簡(jiǎn)單分析了SAR圖像的相干斑噪聲和區(qū)域紋理特點(diǎn),分析比較了現(xiàn)有的SAR圖像分割的兩大類(lèi)方法的優(yōu)缺點(diǎn),根據(jù)兩者的優(yōu)缺點(diǎn)問(wèn)題,提出了一種新的SAR圖像分割方法,該方法以自適應(yīng)窗口提取SAR圖像的低高頻信息作為特征向量,并對(duì)提取的信息進(jìn)行改進(jìn)的FCM分割,通過(guò)與幾種傳統(tǒng)方法結(jié)果的比較,證明了本方法的有效性。2.介紹了支持向量機(jī)在分類(lèi)方面的優(yōu)勢(shì),說(shuō)明了圖像分割在采用支持向量機(jī)算法的技術(shù)實(shí)現(xiàn),采用凸殼性質(zhì)的支持向量機(jī)方法進(jìn)行圖像分割,分析了非局部思想在圖像處理方面的優(yōu)勢(shì),用非局部思想提取頻域信息,并將頻域信息引入支持向量機(jī)的凸殼性質(zhì),提出了一種基于非局部頻域信息和支持向量機(jī)的SAR圖像分割。和經(jīng)典方法對(duì)比實(shí)驗(yàn)結(jié)果表明,本方法能夠達(dá)到更佳的分割效果。3.詳細(xì)研究并介紹了深度學(xué)習(xí)CNN卷積神經(jīng)網(wǎng)絡(luò),并用正交試驗(yàn)設(shè)計(jì)改進(jìn)的PSO粒子群算法調(diào)整網(wǎng)絡(luò),提出了一種基于超像素和正交PSO修正深度學(xué)習(xí)的圖像分割,和其他算法對(duì)比實(shí)驗(yàn)表明,本方法能夠充分提取圖像信息,并在一致區(qū)域和邊緣上達(dá)到很好的分割效果。
[Abstract]:SAR images contain a variety of ground information, which have been widely used in civil and military fields such as target recognition, disaster assessment, environmental monitoring and tracking, and the accurate segmentation of all kinds of targets in images. Sar is of great significance to the subsequent processing of SAR images. Sar has the advantages of all-time and all-weather, but because of the huge amount of data, rich image objects, serious pollution by speckle noise and so on, Sar has the advantages of full time and all-weather. High resolution SAR image processing faces many challenges. Therefore, SAR image segmentation has always been one of the hot research contents in the field of SAR information processing. On the basis of studying the development of SAR image segmentation, this paper considers the characteristics of high resolution SAR image, combined with adaptive frequency domain information and depth learning theory to study SAR image segmentation, the main research contents are as follows: 1. The speckle noise and region texture characteristics of SAR images are briefly analyzed, and the advantages and disadvantages of the two existing SAR image segmentation methods are analyzed and compared. according to the advantages and disadvantages of the two methods, a new SAR image segmentation method is proposed. In this method, the low high frequency information of SAR image is extracted by adaptive window as feature vector, and the extracted information is segmented by improved FCM. Compared with the results of several traditional methods, the effectiveness of this method is proved. 2. This paper introduces the advantages of support vector machine in classification, and explains that image segmentation is realized by using support vector machine (SVM) algorithm, and image segmentation is carried out by using convex hull support vector machine (SVM). The advantages of nonlocal thought in image processing are analyzed. The frequency domain information is extracted by nonlocal idea, and the frequency domain information is introduced into the convex shell property of support vector machine. A SAR image segmentation based on non-local frequency domain information and support vector machine (SVM) is proposed. Compared with the classical method, the experimental results show that this method can achieve better segmentation effect. In this paper, the deep learning CNN convolution neural network is studied and introduced in detail, and an improved PSO particle swarm optimization algorithm is designed to adjust the network by orthogonal experiment. An image segmentation based on super pixel and orthogonal PSO modified depth learning is proposed. Compared with other algorithms, this method can fully extract image information and achieve good segmentation effect on consistent region and edge.
【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(lèi)號(hào)】：TN957.52
本文編號(hào)：2485142
[Abstract]:SAR images contain a variety of ground information, which have been widely used in civil and military fields such as target recognition, disaster assessment, environmental monitoring and tracking, and the accurate segmentation of all kinds of targets in images. Sar is of great significance to the subsequent processing of SAR images. Sar has the advantages of all-time and all-weather, but because of the huge amount of data, rich image objects, serious pollution by speckle noise and so on, Sar has the advantages of full time and all-weather. High resolution SAR image processing faces many challenges. Therefore, SAR image segmentation has always been one of the hot research contents in the field of SAR information processing. On the basis of studying the development of SAR image segmentation, this paper considers the characteristics of high resolution SAR image, combined with adaptive frequency domain information and depth learning theory to study SAR image segmentation, the main research contents are as follows: 1. The speckle noise and region texture characteristics of SAR images are briefly analyzed, and the advantages and disadvantages of the two existing SAR image segmentation methods are analyzed and compared. according to the advantages and disadvantages of the two methods, a new SAR image segmentation method is proposed. In this method, the low high frequency information of SAR image is extracted by adaptive window as feature vector, and the extracted information is segmented by improved FCM. Compared with the results of several traditional methods, the effectiveness of this method is proved. 2. This paper introduces the advantages of support vector machine in classification, and explains that image segmentation is realized by using support vector machine (SVM) algorithm, and image segmentation is carried out by using convex hull support vector machine (SVM). The advantages of nonlocal thought in image processing are analyzed. The frequency domain information is extracted by nonlocal idea, and the frequency domain information is introduced into the convex shell property of support vector machine. A SAR image segmentation based on non-local frequency domain information and support vector machine (SVM) is proposed. Compared with the classical method, the experimental results show that this method can achieve better segmentation effect. In this paper, the deep learning CNN convolution neural network is studied and introduced in detail, and an improved PSO particle swarm optimization algorithm is designed to adjust the network by orthogonal experiment. An image segmentation based on super pixel and orthogonal PSO modified depth learning is proposed. Compared with other algorithms, this method can fully extract image information and achieve good segmentation effect on consistent region and edge.
【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(lèi)號(hào)】：TN957.52
【參考文獻(xiàn)】
相關(guān)期刊論文 前2條
1 鄒煥新,蔣詠梅,匡綱要,郁文賢;一種基于斑點(diǎn)抑制的SAR圖像艦船航跡檢測(cè)算法[J];電子與信息學(xué)報(bào);2003年08期
2 譚炳香,李增元;SAR數(shù)據(jù)在南方水稻分布圖快速更新中的應(yīng)用方法研究[J];國(guó)土資源遙感;2000年01期
，本文編號(hào)：2485142
本文鏈接：http://sikaile.net/kejilunwen/wltx/2485142.html
最近更新
教材專(zhuān)著
