面向?qū)ο蟮母叻直媛蔛AR影像變化檢測(cè)方法研究
本文選題：面向?qū)ο?/strong> + 多尺度分割 ； 參考：《山東科技大學(xué)》2017年碩士論文
【摘要】：遙感影像變化檢測(cè)是通過(guò)對(duì)比同一地區(qū)不同時(shí)相的影像數(shù)據(jù)進(jìn)行地球環(huán)境和安全監(jiān)測(cè)的技術(shù)。由于合成孔徑雷達(dá)(Synthetic Aperture Radar,SAR)全天時(shí)全天候的成像模式,相較于光學(xué)遙感有明顯優(yōu)勢(shì),在變化檢測(cè)領(lǐng)域中發(fā)揮重要作用。高分辨率SAR影像變化檢測(cè)技術(shù)被廣泛應(yīng)用在農(nóng)業(yè)調(diào)查、城市擴(kuò)展監(jiān)測(cè)、自然災(zāi)害評(píng)估等多個(gè)領(lǐng)域,為科學(xué)分析和決策提供保障和服務(wù),已經(jīng)成為國(guó)家發(fā)展規(guī)劃的重要研究?jī)?nèi)容。目前SAR影像非監(jiān)督變化檢測(cè)方法主要分為兩類:像素級(jí)變化檢測(cè)和對(duì)象級(jí)變化檢測(cè)。像素級(jí)變化檢測(cè)方法對(duì)不同影像間輻射度差別、噪聲等因素比較敏感,并且像素級(jí)變化檢測(cè)方法忽略了目標(biāo)的整體性。而對(duì)象級(jí)變化檢測(cè)方法以圖斑為影像分析的處理單元,更符合人類認(rèn)知事物的思維邏輯,并且可綜合利用對(duì)象的強(qiáng)度信息、空間信息和紋理信息。為此,本文以面向?qū)ο蟮乃枷霝檠芯炕A(chǔ),充分利用SAR影像豐富的細(xì)節(jié)信息,以提高SAR影像的變化檢測(cè)精度為目的進(jìn)行深入研究,提出了基于圖斑對(duì)象均值對(duì)數(shù)比的變化檢測(cè)算法和灰度直方圖和LBP紋理直方圖的G統(tǒng)計(jì)量距離自適應(yīng)加權(quán)的變化檢測(cè)方法。本文主要工作和創(chuàng)新點(diǎn)如下:1.總結(jié)變化檢測(cè)方法的研究現(xiàn)狀并分析存在的問(wèn)題,介紹SAR影像特征和常用的SAR影像變化檢測(cè)預(yù)處理方法,分析常用變化檢測(cè)方法及其優(yōu)缺點(diǎn),介紹SAR影像變化檢測(cè)精度評(píng)價(jià)方法。2.歸納總結(jié)SAR影像分割方法,重點(diǎn)介紹了分形網(wǎng)絡(luò)演化分割方法。本文在SAR影像分割前采用非局部三邊濾波方法,相比傳統(tǒng)增強(qiáng)Frost濾波,取得了更好的分割結(jié)果。3.提出了一種基于圖斑對(duì)象均值對(duì)數(shù)比的變化檢測(cè)算法。傳統(tǒng)的對(duì)數(shù)比值法以單個(gè)像素或者像素的中心鄰域?yàn)榛咎幚韱卧?在高分辨率SAR影像進(jìn)行變化檢測(cè)時(shí),像素級(jí)對(duì)數(shù)比值法存在大量檢測(cè)虛警,鄰域均值對(duì)數(shù)比值法損失細(xì)節(jié)信息,檢測(cè)結(jié)果邊緣模糊。本文采用面向?qū)ο蟮乃枷?SAR影像分割后進(jìn)行矢量聯(lián)合,以合并后的圖斑為基本處理單元,計(jì)算各圖斑的灰度均值,圖斑均值進(jìn)行對(duì)數(shù)比值運(yùn)算得到差異圖,該算法可避免斑點(diǎn)噪聲的干擾,同時(shí)保留了變化區(qū)域的邊緣信息。4.提出了灰度直方圖和LBP紋理直方圖的G統(tǒng)計(jì)量距離自適應(yīng)加權(quán)的變化檢測(cè)方法。針對(duì)均值對(duì)數(shù)比值法僅僅依靠SAR影像的灰度信息,在對(duì)建筑物進(jìn)行變化信息檢測(cè)時(shí),SAR影像中建筑物由于高度的影響存在陰影現(xiàn)象,此時(shí)該算法檢測(cè)效果不佳的特點(diǎn)。本文采用面向?qū)ο蟮姆椒?以圖斑對(duì)象為基本的處理單元,計(jì)算灰度直方圖和LBP紋理直方圖,用G統(tǒng)計(jì)量計(jì)算直方圖距離,將灰度直方圖G統(tǒng)計(jì)量距離和LBP紋理直方圖G統(tǒng)計(jì)量距離進(jìn)行自適應(yīng)加權(quán)確定差異圖,采用CFAR算法對(duì)差異圖進(jìn)行閾值分割得到變化二值圖。
[Abstract]:Change detection of remote sensing image is the earth's environment and safety monitoring through the image data of the same area in different time contrast technology. Because the synthetic aperture radar (Synthetic Aperture, Radar, SAR) imaging mode of all-weather and all day long, compared with optical remote sensing has obvious advantages, play an important role in the field of change detection of high resolution changes. SAR image detection technology is widely used in agricultural research, city extension monitoring, many areas of natural disaster assessment, provide support and services for the scientific analysis and decision-making, has become an important research content in the national development plan. The current SAR image detection method of supervision changes are mainly divided into two categories: pixel level change detection and object level change detection. Detection method of pixel level change on different images of different radiation, noise and other factors more sensitive, and the pixel level change detection method is ignored The overall target. While the object level change detection method for patch image analysis processing unit, more in line with the logic of human cognition, and intensity information of comprehensive utilization of objects, spatial information and texture information. Therefore, based on the object-oriented thought as the research basis, make full use of the rich details of the SAR image the changes of SAR images to improve the detection accuracy for the purpose of in-depth research, put forward the G statistic distance map spot changes mean logarithmic ratio detection algorithm and gray histogram and LBP texture histogram adaptive detection method based on weighted changes. This paper mainly work and innovation are as follows: 1. summarize the research status change detection method and analyze the existing problem, the pretreatment method of SAR features and SAR image change detection and analysis of common change detection methods and their advantages and disadvantages are introduced. SAR image change detection method for accuracy evaluation of.2. induction methods of SAR image segmentation, introduces the segmentation method of fractal net evolution. Based on the SAR image segmentation by non local three edge filtering method, compared with the traditional enhanced Frost filter has better segmentation results of.3. proposed a map object changes than the logarithmic mean the detection algorithm based on logarithmic ratio method. The traditional neighborhood center to a single pixel or pixel as the basic processing unit, change detection in SAR images with high resolution, pixel level log ratio method has a large number of false alarm detection, neighborhood average logarithmic ratio method the loss of detail information, fuzzy edge detection results. This paper uses the object oriented thinking SAR image segmentation after vector combination, combined with patches as the basic processing unit, the calculation of gray mean patch, patch mean logarithmic ratio. The difference is, this algorithm can avoid the interference of speckle noise, while preserving the edge information.4. change area detection method is proposed gray histogram and LBP texture histogram G statistic distance adaptive weighted changes. According to mean logarithmic ratio method only depend on the gray information of SAR image, the change detection of building SAR, image building due to a high degree of influence of the shadow phenomenon, the characteristics of poor detection effect of the algorithm. This paper uses the method of object oriented, patch object is the basic processing units, calculate the gray histogram and LBP texture histogram, histogram distance calculated by G statistics, the gray histogram and LBP texture histogram statistics from G the G statistic distance by adaptive weighted CFAR algorithm is used to determine the difference map segmentation obtained two value image of difference map.
【學(xué)位授予單位】：山東科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：P237;TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 李亮;梁彬;薛鵬;應(yīng)國(guó)偉;;基于像斑直方圖G統(tǒng)計(jì)量的遙感影像分類[J];國(guó)土資源遙感;2016年04期
2 公茂果;蘇臨之;李豪;劉嘉;;合成孔徑雷達(dá)影像變化檢測(cè)研究進(jìn)展[J];計(jì)算機(jī)研究與發(fā)展;2016年01期
3 蔡利平;史文中;張華;苗則朗;何鵬飛;;邊緣走向自適應(yīng)的多尺度分水嶺分割算法[J];中國(guó)礦業(yè)大學(xué)學(xué)報(bào);2015年04期
4 劉永春;王廣學(xué);栗蘋;閆曉鵬;;基于二維概率密度函數(shù)比較的SAR圖像變化檢測(cè)方法[J];電子與信息學(xué)報(bào);2015年05期
5 徐德偉;茹卉;宋輝;楊文;;基于直接密度比估計(jì)的SAR圖像變化檢測(cè)[J];現(xiàn)代雷達(dá);2015年02期
6 馮策;戴樹嶺;趙帥和;;基于顯著特性的保持邊緣濾波算法[J];北京航空航天大學(xué)學(xué)報(bào);2015年04期
7 李亮;舒寧;王凱;龔煈;;融合多特征的遙感影像變化檢測(cè)方法[J];測(cè)繪學(xué)報(bào);2014年09期
8 張紅;葉曦;王超;張波;吳樊;湯益先;;面向?qū)ο蟮母叻直媛蔛AR圖像處理及應(yīng)用[J];中國(guó)圖象圖形學(xué)報(bào);2014年03期
9 夏朝旭;何政偉;于歡;王東輝;葉嬌瓏;;面向?qū)ο蟮耐恋馗脖蛔兓瘷z測(cè)研究[J];遙感技術(shù)與應(yīng)用;2014年01期
10 李亮;龔煈;李雪;王凱;;像斑直方圖相似性測(cè)度的高分辨率遙感影像變化檢測(cè)[J];遙感學(xué)報(bào);2014年01期
相關(guān)博士學(xué)位論文 前3條
1 黃志堅(jiān);面向?qū)ο笥跋穹治鲋械亩喑叨确椒ㄑ芯縖D];國(guó)防科學(xué)技術(shù)大學(xué);2014年
2 咼維;城市地區(qū)高分辨率SAR圖像中典型地物的特征分析與解譯[D];武漢大學(xué);2010年
3 黃勇;SAR圖像變化檢測(cè)及相關(guān)技術(shù)研究[D];電子科技大學(xué);2006年
相關(guān)碩士學(xué)位論文 前9條
1 趙玉丹;基于LBP的圖像紋理特征的提取及應(yīng)用[D];西安郵電大學(xué);2015年
2 郝慮遠(yuǎn);基于紋理分析的高分辨率影像面向?qū)ο蠓诸愌芯縖D];北京師范大學(xué);2014年
3 沈蕾;基于廣義Gamma分布的SAR圖像變化檢測(cè)[D];西南交通大學(xué);2013年
4 王虎清;基于廣義Gamma混合模型的遙感圖像變化檢測(cè)研究[D];西南交通大學(xué);2012年
5 王剛;基于影像分割的SAR影像變化檢測(cè)技術(shù)研究[D];解放軍信息工程大學(xué);2012年
6 付磊;基于局部信息統(tǒng)計(jì)的SAR圖像變化檢測(cè)[D];西安電子科技大學(xué);2012年
7 蘭遠(yuǎn)鴿;基于SAR影像的變化檢測(cè)技術(shù)研究[D];解放軍信息工程大學(xué);2010年
8 黃晶;基于分形維度與灰度共生矩陣的圖像分類研究[D];武漢理工大學(xué);2008年
9 許冠軍;數(shù)字圖像去噪算法研究[D];浙江大學(xué);2006年
，本文編號(hào)：1751680
本文鏈接：http://sikaile.net/kejilunwen/dizhicehuilunwen/1751680.html
