本文關(guān)鍵詞： 高分辨率遙感 圖像分割 克隆選擇 模糊C均值聚類 譜嵌入式聚類 核函數(shù)　出處：《中國(guó)礦業(yè)大學(xué)》2014年博士論文　論文類型：學(xué)位論文

【摘要】：隨著遙感技術(shù)的不斷發(fā)展，利用新的遙感平臺(tái)獲取的高分辨率圖像不但光譜信息豐富，同時(shí)包含著大量地物表面更多的形狀、紋理等細(xì)節(jié)信息。但是隨之而來(lái)的挑戰(zhàn)是如何對(duì)這些數(shù)據(jù)進(jìn)行有效的處理，為后續(xù)的具體應(yīng)用提供支持。遙感圖像分割是數(shù)據(jù)分析理解前的關(guān)鍵步驟，圖像分割效果的好壞將直接影響到后續(xù)的目標(biāo)特征提取描述、識(shí)別與分類。 該文圍繞提高高分辨遙感圖像的分割性能這一中心環(huán)節(jié)，在對(duì)圖像分割研究中使用的克隆選擇算法（Clonal Selection Algorithm，CS）、譜嵌入式聚類方法（Spectral Embedded Clustering，，SEC）以及模糊C均值聚類（Fuzzy C-meansClustering，F(xiàn)CM）進(jìn)行分析比較的基礎(chǔ)上，結(jié)合遙感圖像的特點(diǎn)從理論、方法上進(jìn)行改進(jìn)，提出了相應(yīng)的改進(jìn)算法，利用QuickBird高分辨率遙感圖像對(duì)相關(guān)分割算法進(jìn)行了試驗(yàn)、評(píng)價(jià)和對(duì)比。 該文主要研究工作如下： 首先，通過(guò)深入分析人工免疫理論中的克隆選擇機(jī)理，針對(duì)基本克隆選擇算法（Clonal Selection Algorithm）存在的不足，通過(guò)增加交叉操作及根據(jù)抗體濃度調(diào)節(jié)種群規(guī)模，提出了改進(jìn)的克隆選擇算法，達(dá)到了提高抗體多樣性，提高算法全局搜索能力的目標(biāo)。通過(guò)與二維最大熵和多重空間構(gòu)造圖像分割方法相結(jié)合，利用實(shí)驗(yàn)證明了改進(jìn)算法優(yōu)于基本克隆算法。 其次，針對(duì)譜聚類算法（Spectral Clustering，SC）和譜嵌入式聚類的缺點(diǎn)，引入核函數(shù)設(shè)計(jì)了基于核函數(shù)的譜嵌入式聚類算法（Kernel Function-based SpectralEmbedded Clustering，KSEC），使用三類核函數(shù)對(duì)算法進(jìn)行了構(gòu)造和實(shí)現(xiàn)，將譜嵌入式聚類和基于核函數(shù)的譜嵌入式聚類算法應(yīng)用于遙感圖像的分割，提高了分割的精度。 第三，在對(duì)模糊C均值聚類（Fuzzy C-means Clustering，F(xiàn)CM）及改進(jìn)模糊C均值聚類算法進(jìn)行研究的基礎(chǔ)上，引入圖像相鄰像素之間的空間引力概念，適度納入局部空間信息和灰度信息，提出了一種基于空間引力的模糊局部信息C均值聚類（Neighborhood-Attraction-Based Fuzzy Local Information C-means Clustering，F(xiàn)LNAICM），克服了圖像中相鄰像素對(duì)中心像素的影響及噪聲對(duì)分割結(jié)果的影響問(wèn)題，成功應(yīng)用到遙感圖像分割中，并取得了比前2種算法更好的分割效果。 最后，通過(guò)對(duì)3種改進(jìn)算法對(duì)遙感圖像分割精度的對(duì)比，證明對(duì)具有模糊特性的遙感圖像進(jìn)行分割時(shí)，基于模糊理論的聚類分割方法更為有效。
[Abstract]:With the development of remote sensing technology, the high-resolution images obtained by the new remote sensing platform are not only rich in spectral information, but also contain more shapes on the surface of a large number of ground objects. However, the challenge is how to deal with these data effectively and provide support for subsequent applications. Remote sensing image segmentation is a key step before data analysis and understanding. The effect of image segmentation will directly affect the target feature extraction description, recognition and classification. This paper focuses on improving the segmentation performance of high resolution remote sensing images. Based on the analysis and comparison of Clonal Selection algorithm, Spectral Embedded clustering algorithm and Fuzzy C-Means clustering algorithm used in image segmentation, this paper improves the theory and method of remote sensing image combining with the characteristics of remote sensing image, the spectral embedded clustering method (Spectral Embedded clustering algorithm) and fuzzy C-means clustering algorithm (FCM). An improved algorithm is proposed, and the correlation segmentation algorithm is tested, evaluated and compared with QuickBird high resolution remote sensing image. The main work of this paper is as follows:. First of all, by analyzing the mechanism of clone selection in artificial immune theory, aiming at the shortcomings of basic clone selection algorithm, by increasing cross-operation and adjusting population size according to antibody concentration, An improved clonal selection algorithm is proposed to improve the diversity of antibodies and improve the global search ability of the algorithm. The experimental results show that the improved algorithm is superior to the basic clone algorithm. Secondly, aiming at the shortcomings of spectral clustering algorithm (Spectral clustering) and spectral embedded clustering, a kernel function based spectral embedded clustering algorithm, Kernel Function-based SpectralEmbedded clustering algorithm, is designed, and the algorithm is constructed and implemented using three kernel functions. The spectral embedded clustering algorithm and the spectral embedded clustering algorithm based on kernel function are applied to the remote sensing image segmentation, which improves the segmentation accuracy. Thirdly, based on the research of fuzzy C-means clustering and improved fuzzy C-means clustering algorithm, the concept of spatial gravity between adjacent pixels is introduced, and local spatial information and gray level information are appropriately incorporated. In this paper, a fuzzy local information clustering method based on spatial gravity is proposed, which is based on fuzzy local information, Attraction-Based Fuzzy Local Information C-means clustering algorithm. It overcomes the influence of adjacent pixels on center pixels and noise on segmentation results, and is successfully applied to remote sensing image segmentation. The segmentation effect is better than the first two algorithms. Finally, by comparing the accuracy of remote sensing image segmentation with three improved algorithms, it is proved that the clustering segmentation method based on fuzzy theory is more effective when the remote sensing image with fuzzy characteristics is segmented.
【學(xué)位授予單位】：中國(guó)礦業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉向華;周蔭清;孫慕涵;;基于快速退火MRF的改進(jìn)SAR圖像分割方法[J];北京航空航天大學(xué)學(xué)報(bào);2010年06期

2 明冬萍,駱劍承,沈占鋒,汪閩,盛昊;高分辨率遙感影像信息提取與目標(biāo)識(shí)別技術(shù)研究[J];測(cè)繪科學(xué);2005年03期

3 楊新;黃順吉;;基于偏微分方程的多區(qū)域SAR圖像分割方法研究[J];電波科學(xué)學(xué)報(bào);2008年03期

4 鐘燕飛;張良培;;高光譜影像特征選擇的快速克隆選擇算法(英文)[J];Geo-Spatial Information Science;2009年03期

5 譚玉敏;槐建柱;唐中實(shí);;基于鄰接圖的面向?qū)ο筮b感圖像分割算法[J];大連海事大學(xué)學(xué)報(bào);2009年02期

6 焦李成,杜海峰;人工免疫系統(tǒng)進(jìn)展與展望[J];電子學(xué)報(bào);2003年10期

7 范九倫;趙鳳;;灰度圖像的二維Otsu曲線閾值分割法[J];電子學(xué)報(bào);2007年04期

8 王玲;薄列峰;焦李成;;密度敏感的譜聚類[J];電子學(xué)報(bào);2007年08期

9 何寧;張朋;;基于邊緣和區(qū)域信息相結(jié)合的變分水平集圖像分割方法[J];電子學(xué)報(bào);2009年10期

10 許新征;丁世飛;史忠植;賈偉寬;;圖像分割的新理論和新方法[J];電子學(xué)報(bào);2010年S1期

相關(guān)博士學(xué)位論文 前2條

1 侯葉;基于圖論的圖像分割技術(shù)研究[D];西安電子科技大學(xué);2011年

2 袁建軍;基于偏微分方程圖像分割技術(shù)的研究[D];重慶大學(xué);2012年

本文編號(hào)：1526298