長(zhǎng)汀縣Spot5影像多尺度分割與信息提取方法研究
發(fā)布時(shí)間：2018-01-15 02:08
本文關(guān)鍵詞：長(zhǎng)汀縣Spot5影像多尺度分割與信息提取方法研究 出處：《福建師范大學(xué)》2015年碩士論文 論文類型：學(xué)位論文
更多相關(guān)文章： Spot5 面向?qū)ο笮畔⑻崛?/b> 高分辨率影像 多尺度分割 模糊規(guī)則
【摘要】：本文以Spot5高分辨率衛(wèi)星遙感影像作為數(shù)據(jù)源,以福建省長(zhǎng)汀縣為試驗(yàn)區(qū),開展了對(duì)長(zhǎng)汀縣2010年Spot5高分辨率遙感影像的多尺度分割和地物信息提取的研究。首先,針對(duì)Spot5衛(wèi)星遙感影像的特點(diǎn),進(jìn)行遙感影像的預(yù)處理。然后對(duì)影像進(jìn)行多尺度分割,確定最合適的分割尺度和形狀因子、緊湊度因子設(shè)置值,得到適宜各地物信息提取對(duì)象,并根據(jù)不同分割尺度確定各地物類別的分類層次。最后,結(jié)合使用模糊數(shù)學(xué)分類方法和最鄰近分類方法得到分類結(jié)果,并使用混淆矩陣對(duì)分類結(jié)果進(jìn)行精度分析。得到如下結(jié)論：(1)多尺度分割參數(shù)設(shè)置上,“尺度”為150時(shí)對(duì)河流、道路和工廠廠房能夠呈現(xiàn)比較完整且均質(zhì)的對(duì)象；“尺度”為50時(shí)建筑物、耕地和植被覆蓋地等呈現(xiàn)比較理想的分割對(duì)象。(2)分割參數(shù)試驗(yàn)中當(dāng)形狀因子設(shè)置為0.2,緊湊度因子設(shè)置為0.5時(shí),分割的影像對(duì)象最為理想。(3)植被覆蓋地信息提取模糊規(guī)則為“標(biāo)準(zhǔn)化植被指數(shù)”=0.06且“亮度”89,水體信息提取模糊規(guī)則為65“近紅外波段的光譜均值3”78.3,道路信息提取模糊規(guī)則為0.3“密度”1,農(nóng)田信息提取模糊規(guī)則為-0.006“標(biāo)準(zhǔn)化植被指數(shù)”0.09,建筑用地信息提取規(guī)則為1“邊境指數(shù)”1.82且0.03“紋理同質(zhì)性”0.13,對(duì)剩余未能很好提取的類別選取訓(xùn)練樣本進(jìn)行最鄰近分類法進(jìn)行提取。(4)最后將提取結(jié)果以長(zhǎng)汀縣2011年國(guó)土調(diào)查數(shù)據(jù)為參考進(jìn)行精度評(píng)價(jià),得到總體分類精度93.73%,Kappa系數(shù)為0.77。
[Abstract]:In this paper, Spot5 high-resolution satellite remote sensing image is used as the data source and Changting County in Fujian Province as the experimental area. In this paper, the multi-scale segmentation and feature extraction of Spot5 high-resolution remote sensing images in Changting County in 2010 were studied. Firstly, the characteristics of Spot5 satellite remote sensing images were analyzed. The preprocessing of remote sensing image is carried out. Then the multi-scale segmentation is carried out to determine the most appropriate segmentation scale and shape factor and the set value of compactness factor. And according to the different segmentation scale to determine the classification level of the local categories. Finally, combined with the use of fuzzy mathematics classification method and the nearest neighbor classification method to obtain the classification results. The accuracy of the classification results is analyzed by using the confusion matrix. The following conclusion is drawn: 1) when the scale is 150, the multi-scale segmentation parameters are set up for the rivers. Roads and factory buildings can present relatively complete and homogeneous objects; When "scale" is 50, buildings, cultivated land and vegetation cover show ideal segmentation object.) in the experiment, when the shape factor is set to 0.2, the compactness factor is set to 0.5. The fuzzy rule of extracting vegetation cover information is "standardized vegetation index" (0.06) and "brightness" (89). The fuzzy rule of extracting water information was 65 "near infrared spectral mean 3" 78.3, and the fuzzy rule of road information extraction was 0.3 "density" 1. The fuzzy rules of farmland information extraction were -0.006 "standardized vegetation index" 0.09, and the rules of information extraction of construction land were 1 "border index" 1.82 and 0.03 "texture homogeneity" 0.13. At last, the precision evaluation was carried out based on the land survey data of Changting County in 2011. The overall classification accuracy of 93.73 kappa coefficient is 0.77.
【學(xué)位授予單位】：福建師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：P237
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 胡潭高;朱文泉;陽小瓊;潘耀忠;張錦水;;高分辨率遙感圖像耕地地塊提取方法研究[J];光譜學(xué)與光譜分析;2009年10期
2 馮益明;鄭冬梅;智長(zhǎng)貴;姚愛冬;高志海;;面向?qū)ο蟮纳郴恋匦畔⑻崛J];林業(yè)科學(xué);2013年01期
3 錢巧靜,謝瑞,張磊,顏長(zhǎng)珍,吳炳方;面向?qū)ο蟮耐恋馗采w信息提取方法研究[J];遙感技術(shù)與應(yīng)用;2005年03期
4 張秀英;楊敏華;劉常娟;王振興;;面向?qū)ο筮b感分類新技術(shù)在第二次土地調(diào)查中的應(yīng)用[J];遙感信息;2008年03期
相關(guān)博士學(xué)位論文 前1條
1 柳稼航;基于視覺特征的高分辨率光學(xué)遙感影像目標(biāo)識(shí)別與提取技術(shù)研究[D];上海交通大學(xué);2011年
相關(guān)碩士學(xué)位論文 前2條
1 李莉;面向?qū)ο蟮母叻直媛蔬b感影像信息提取研究[D];成都理工大學(xué);2012年
2 詹福雷;基于面向?qū)ο蟮母叻直媛蔬b感影像信息提取[D];吉林大學(xué);2014年
，本文編號(hào)：1426304
本文鏈接：http://sikaile.net/kejilunwen/dizhicehuilunwen/1426304.html
最近更新
教材專著
