本文選題：高空間分辨率遙感影像　切入點(diǎn)：影像分割　出處：《長安大學(xué)》2016年博士論文　論文類型：學(xué)位論文

【摘要】：隨著遙感對(duì)地觀測(cè)技術(shù)的不斷進(jìn)步,遙感影像的空間分辨率越來越高,高空間分辨率影像為遙感技術(shù)的發(fā)展帶來機(jī)遇的同時(shí),也由于自身的特點(diǎn)為遙感數(shù)據(jù)的處理帶來了新的挑戰(zhàn),導(dǎo)致傳統(tǒng)的像素級(jí)處理方法不能適應(yīng)當(dāng)前遙感分析與應(yīng)用的需求,在這種情況下,面向?qū)ο蠹夹g(shù)成為高分辨率遙感影像分析的新選擇。然而,面向?qū)ο蠓治鲈诶碚摵图夹g(shù)上并未達(dá)到成熟,仍然有許多問題亟待研究和解決,突出表現(xiàn)在遙感影像分割這一基礎(chǔ)環(huán)節(jié),目前已有的研究仍然存在不同程度的局限性,如分割精度與效率的不足、模型的適應(yīng)性差、缺乏統(tǒng)一的尺度評(píng)價(jià)標(biāo)準(zhǔn)等。本文針對(duì)現(xiàn)有研究工作中的不足,重點(diǎn)對(duì)高空間分辨率遙感影像的分割及多尺度分割中的最優(yōu)分割尺度選擇問題進(jìn)行了探索與討論,主要研究內(nèi)容與成果如下:(1)提出了一種基于區(qū)域合并的遙感影像快速分割方法。該方法首先通過分水嶺變換得到影像的初始分割區(qū)域,然后采用局部尋優(yōu)的策略對(duì)初分割區(qū)域進(jìn)行合并得到最終分割結(jié)果。在區(qū)域合并過程中,針對(duì)傳統(tǒng)的區(qū)域鄰接圖效率較低的問題,設(shè)計(jì)了鄰域數(shù)組的數(shù)據(jù)結(jié)構(gòu)來維護(hù)區(qū)域之間的鄰接關(guān)系,該數(shù)據(jù)結(jié)構(gòu)相比鄰接圖具有更高的效率,為兼顧算法的精度,方法將區(qū)域合并過程分為兩個(gè)步驟進(jìn)行,在合并準(zhǔn)則中綜合考慮了區(qū)域的光譜、幾何和紋理信息。通過與傳統(tǒng)的基于鄰接圖的區(qū)域類分割算法的對(duì)比,證明了算法在分割效率和精度上的優(yōu)勢(shì)。(2)提出了一種融合影像多種特征的多尺度分割方法。該方法也屬于區(qū)域類的分割算法,在區(qū)域合并時(shí)綜合利用影像的光譜、紋理、形狀等特征來構(gòu)建對(duì)象的語義描述并建立合并規(guī)則,以解決影像特征利用不足而導(dǎo)致分割精度較低的問題,算法引入非下采樣輪廓波變換并結(jié)合模糊聚類分析來計(jì)算對(duì)象的紋理特征距離。在合并過程中采用全局尋優(yōu)的策略保證了方法的多尺度特性,并聯(lián)合采用鄰接圖和最優(yōu)鄰圖兩種圖模型來維護(hù)區(qū)域的鄰接關(guān)系,保證了算法的效率。通過與其它算法的對(duì)比,證明了算法在精度和效率上已可匹敵同類商業(yè)軟件。(3)提出了一種遙感影像最優(yōu)分割尺度的監(jiān)督評(píng)價(jià)方法。該方法根據(jù)參考對(duì)象和分割對(duì)象的相似性來構(gòu)建分割尺度評(píng)價(jià)函數(shù),通過計(jì)算評(píng)價(jià)函數(shù)值來確定最優(yōu)分割尺度。采用統(tǒng)計(jì)直方圖來進(jìn)行灰度相似性的計(jì)算,克服了其它特征進(jìn)行對(duì)象灰度描述時(shí)的不準(zhǔn)確性,通過構(gòu)建形狀描述函數(shù)進(jìn)行形狀相似性計(jì)算,能夠?qū)?duì)象的幾何差異作出較為準(zhǔn)確的判斷。通過實(shí)驗(yàn)將該方法與較為成熟的人為試錯(cuò)法相比,驗(yàn)證了算法的有效性。(4)發(fā)展了一種基于面向?qū)ο蟮母叻直媛蔬b感影像道路提取方法。該方法首先應(yīng)用本文提出的分割算法及最優(yōu)分割尺度評(píng)價(jià)方法得到道路影像在最優(yōu)尺度下的分割結(jié)果,然后通過構(gòu)建道路知識(shí)庫,并進(jìn)行地物特征的計(jì)算,來實(shí)現(xiàn)道路的初步提取;最后對(duì)道路初始提取結(jié)果進(jìn)行多方向形態(tài)學(xué)濾波,以去除特征相似的混疊地物,優(yōu)化道路提取結(jié)果,并對(duì)優(yōu)化后結(jié)果進(jìn)行細(xì)化及連接處理,從而實(shí)現(xiàn)道路網(wǎng)的提取。實(shí)驗(yàn)結(jié)果表明,該方法能較好地從復(fù)雜遙感影像中提取道路網(wǎng)。
[Abstract]:With the remote sensing of earth observation technology continues to progress, the spatial resolution of remote sensing images more and more high, the high spatial resolution image brings opportunities for the development of remote sensing technology at the same time, but also because of their own characteristics for the processing of remote sensing data has brought new challenges, leading to the traditional pixel level processing method can not adapt to the current remote sensing analysis and application the demand, in this case, the object oriented technology has become a new choice of high resolution remote sensing images. However, object oriented analysis has not reached maturity in theory and technology, there are still many problems to solve, especially in the remote sensing image segmentation is a basic step, the existing research still has limitations the degree, such as the lack of segmentation accuracy and efficiency, the adaptability of the model is poor, lack of unified evaluation standard scale. Based on the existing research work in Lack of focus on the optimal segmentation of high spatial resolution remote sensing image segmentation and multi-scale segmentation scale selection problems are discussed. The main research contents and results are as follows: (1) proposed a fast segmentation method of remote sensing image based on region merging. This method firstly by the initial watershed transform to obtain image segmentation region, and then uses a local optimization strategy of early segmentation region merging to get the segmentation result. In the process of region merging, the traditional region adjacency graph and the problem of low efficiency, the data structure is designed to maintain the number of neighborhood group adjacency relation between regions, compared to the data structure graph is more efficient for both, the accuracy of the algorithm, the method of region merging process is divided into two steps, in the region merging criterion in spectra considering geometric and texture information. With the comparison of adjacency graph area segmentation algorithm based on the traditional algorithm, show the advantage in the segmentation efficiency and accuracy. (2) proposed a segmentation method based on multi-scale fusion multi feature of image segmentation algorithm. This method also belongs to the area, in the area with comprehensive use of image spectrum. The texture, shape and other characteristics to construct the object semantic description and establish merger rules to solve the shortage of image features using the low precision problem of segmentation algorithm is introduced, Nonsubsampled contourlet transform and fuzzy clustering analysis to calculate the distance of texture feature images. In the process of merging with global optimization strategy the multi-scale characteristic method, and combined with the adjacency graph and the optimal neighborhood graph two graph model to maintain relationship between adjacent areas, to ensure the efficiency of the algorithm. By comparing with other algorithms, proved The algorithm in accuracy and efficiency have been unmatched similar commercial software. (3) proposed a supervision and evaluation method of remote sensing image optimal segmentation scale. According to the similarity of the reference object and object segmentation to construct the segmentation scale evaluation function, through the calculation to determine the optimal segmentation scale by statistical histogram evaluation function. Calculate the similarity of gray, overcome the other characteristics of the intensity of the object description inaccuracy, by constructing a shape similarity calculation function of describing the shape of the object to the geometrical differences to make more accurate judgments. The experiment will be compared with the mature method of trial and error method, verify the validity of the algorithm. (4) developed a road extraction method of high resolution remote sensing image based on object oriented segmentation algorithm and optimal scale. Firstly, this paper presents the application of The evaluation method of road image segmentation result is obtained in the optimal scale, and then through the construction of road knowledge base, and compute the features extracted, to achieve the road; finally, multi direction morphological filtering for initial road extraction results, similar to mixed stack objects removal characteristics, optimization of road extraction results, and the optimized the results of refinement and connection processing, so as to realize road extraction. The experimental results show that this method can effectively extract the road network from the complex remote sensing image.

【學(xué)位授予單位】：長安大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：P237

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 付卓;胡吉平;譚衢霖;劉正軍;;遙感應(yīng)用分析中影像分割方法[J];遙感技術(shù)與應(yīng)用;2006年05期

2 徐芳,梅文勝,張志華;航空影像分割的最小二乘支持向量機(jī)方法[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2005年08期

3 高偉;劉修國;彭攀;陳啟浩;;一種改進(jìn)的高分辨率遙感影像分割方法[J];地球科學(xué)(中國地質(zhì)大學(xué)學(xué)報(bào));2010年03期

4 闞曉云;孫景振;王紅偉;;無人機(jī)影像分割尺度及地物分類研究[J];科技廣場(chǎng);2013年11期

5 洪志佳;;面向?qū)ο笮畔⑻崛≈杏跋穹指顓?shù)的選擇[J];河南科技;2014年10期

6 李景文;張紫萍;郭偉立;蘇浩;羅文彬;;基于分水嶺與多尺度相結(jié)合的影像分割方法[J];廣西師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年01期

7 張煜,張祖勛,張劍清;幾何約束與影像分割相結(jié)合的快速半自動(dòng)房屋提取[J];武漢測(cè)繪科技大學(xué)學(xué)報(bào);2000年03期

8 肖奧;趙文吉;;基于最小異質(zhì)性區(qū)域生長法的多尺度城市地物影像分割[J];首都師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年01期

9 蘇偉;李京;陳云浩;張錦水;胡德勇;劉翠敏;;基于多尺度影像分割的面向?qū)ο蟪鞘型恋馗脖环诸愌芯俊择R來西亞吉隆坡市城市中心區(qū)為例[J];遙感學(xué)報(bào);2007年04期

10 盛慶紅;張劍清;肖暉;;基于顏色和紋理的森林影像分割方法[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2008年03期

相關(guān)會(huì)議論文 前1條

1 莫登奎;林輝;;一種穩(wěn)健的高分辨率遙感影像分割方法[A];第十二屆全國圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2005年

相關(guān)博士學(xué)位論文 前1條

1 劉大偉;高分辨率遙感影像分割方法及應(yīng)用研究[D];長安大學(xué);2016年

相關(guān)碩士學(xué)位論文 前7條

1 張愛竹;基于智能優(yōu)化算法的高分辨率震害影像分割[D];中國石油大學(xué)(華東);2014年

2 莆杰藝;基于異質(zhì)性最小準(zhǔn)則的基元合并影像分割方法研究[D];長安大學(xué);2013年

3 黃亮;一種融合邊緣與對(duì)象異質(zhì)性的影像分割算法[D];昆明理工大學(xué);2011年

4 袁秀華;高分辨率遙感影像分割研究[D];江西理工大學(xué);2014年

5 王博;基于高分辨率影像的改進(jìn)分水嶺算法影像分割參數(shù)優(yōu)選研究[D];蘭州大學(xué);2013年

6 呂佩育;基于影像分割的無人機(jī)影像密集匹配算法研究與實(shí)現(xiàn)[D];西安科技大學(xué);2013年

7 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

，

本文編號(hào)：1574089