【摘要】：隨著“一帶一路”與新型城鎮(zhèn)化戰(zhàn)略決策的推動(dòng)與實(shí)施,中國(guó)在未來(lái)幾十年中發(fā)展的空間格局將發(fā)生巨大改變。自1978年改革開(kāi)放以來(lái),我國(guó)的經(jīng)濟(jì)迅猛增長(zhǎng),在短時(shí)間內(nèi)躍居全球前列,社會(huì)和諧發(fā)展,國(guó)民的生活質(zhì)量有了明顯的提升,居民地的擴(kuò)張速度也愈來(lái)愈快。對(duì)居民地進(jìn)行快速準(zhǔn)確地識(shí)別和提取在推進(jìn)國(guó)家戰(zhàn)略決策,實(shí)現(xiàn)數(shù)字城市,輔助城市規(guī)劃等多個(gè)領(lǐng)域具有重大的現(xiàn)實(shí)意義。高分四號(hào)(GF-4)衛(wèi)星作為我國(guó)實(shí)施高分辨率對(duì)地觀測(cè)系統(tǒng)的重要組成部分,能夠及時(shí)有效識(shí)別地面變化,有效支撐地震、洪澇、干旱、臺(tái)風(fēng)等自然災(zāi)害救助、氣候變化研究、林業(yè)及水資源環(huán)境調(diào)查等重大行業(yè)應(yīng)用。本論文利用GF-4衛(wèi)星影像,結(jié)合其高時(shí)譜這一特性,提取并分析居民地與其他地類的光譜特征差異,并結(jié)合時(shí)序光譜使用不同方法對(duì)居民地信息進(jìn)行識(shí)別和提取。論文從以下幾個(gè)部分展開(kāi):首先,介紹了本論文的研究背景和意義,再介紹與論文主題息息相關(guān)的遙感信息提取技術(shù)和居民地識(shí)別提取技術(shù)的研究現(xiàn)狀與進(jìn)展,并提出研究?jī)?nèi)容及技術(shù)路線。接著,介紹了GF-4衛(wèi)星影像,并對(duì)影像進(jìn)行預(yù)處理以消除來(lái)自各方面的誤差。然后,通過(guò)對(duì)GF-4影像的典型地物光譜指數(shù)特征的分析,提出基于光譜特征決策樹(shù)的居民地信息提取方法,進(jìn)而對(duì)時(shí)序光譜指數(shù)特征進(jìn)行分析,提出基于時(shí)序光譜特征決策樹(shù)的居民地信息提取方法,在此基礎(chǔ)上將時(shí)序光譜指數(shù)特征和深度學(xué)習(xí)技術(shù)同時(shí)引入居民地信息識(shí)別提取中,提出基于時(shí)序光譜特征全卷積神經(jīng)網(wǎng)絡(luò)的居民地信息提取方法。最終對(duì)三種方法的實(shí)驗(yàn)結(jié)果進(jìn)行對(duì)比分析,得出結(jié)論。通過(guò)上述研究的開(kāi)展,本論文可得到以下主要結(jié)論:(1)太陽(yáng)高度角的變化不僅僅影響了地物光譜的大小,甚至對(duì)地物光譜的變化率大小和變化率變化的快慢也有一定的影響,且不同地物類型的光譜特征隨太陽(yáng)高度角的變化特征也有所不同。(2)當(dāng)使用決策樹(shù)方法時(shí),結(jié)合時(shí)序光譜特征對(duì)居民地信息進(jìn)行提取相較于僅結(jié)合光譜特征的提取來(lái)說(shuō),將提取精度由89.85%提升到93.38%。(3)利用全卷積神經(jīng)網(wǎng)絡(luò)可提升基于時(shí)序光譜特征居民地信息提取的提取精度,提取精度由93.38%提升到95.15%。此外,本論文有以下創(chuàng)新點(diǎn):(1)將時(shí)序光譜特征與太陽(yáng)高度角的關(guān)系引入到?jīng)Q策樹(shù)模型中,相比較僅利用光譜特征的居民地提取方法而言,精度有所提高。(2)將時(shí)序光譜特征與深度學(xué)習(xí)中全卷積神經(jīng)網(wǎng)絡(luò)方法相結(jié)合,較不考慮時(shí)序光譜特征或不采用深度學(xué)習(xí)的其他提取方法來(lái)說(shuō),更加提升了分類提取精度。研究基于GF-4衛(wèi)星遙感影像時(shí)序光譜的居民地識(shí)別提取方法,為減災(zāi)、防災(zāi)、推進(jìn)城鎮(zhèn)化進(jìn)程、城市精細(xì)化管理和國(guó)土資源管理等工作快速提供動(dòng)態(tài)更新數(shù)據(jù),并為我國(guó)國(guó)產(chǎn)高分系列衛(wèi)星數(shù)據(jù)遙感產(chǎn)品的應(yīng)用提供技術(shù)與方法支撐和示范指導(dǎo)作用。
[Abstract]:With the promotion and implementation of "The Belt and Road Initiative" and the strategic decision of new urbanization, the spatial pattern of China's development in the coming decades will be greatly changed. Since the reform and opening up in 1978, the economy of our country has been growing rapidly, it has leaped to the forefront of the world in a short period of time, the harmonious development of the society, the quality of life of the people has been obviously improved, and the speed of the expansion of the residential land has also become more and more rapid. Rapid and accurate identification and extraction of residential land is of great practical significance in promoting national strategic decision-making, realizing digital city, assisting urban planning and so on. As an important part of China's high-resolution Earth observation system, the GF-4 satellite can effectively identify ground changes in a timely manner and effectively support natural disasters such as earthquakes, floods, droughts, typhoons, and so on. Climate change research, forestry and water resources environmental survey and other major industry applications. In this paper, we use GF-4 satellite image and its high-time spectrum to extract and analyze the difference of spectral features between residential land and other land classes, and use different methods to identify and extract resident land information combined with temporal spectrum. The thesis starts from the following parts: firstly, this paper introduces the research background and significance of this paper, and then introduces the research status and progress of remote sensing information extraction technology and residential identification extraction technology, which are closely related to the subject of the thesis. And put forward the research content and technical route. Then, the GF-4 satellite image is introduced, and the image is pre-processed to eliminate the errors from various aspects. Then, by analyzing the spectral index characteristics of typical ground objects in GF-4 images, a method of extracting resident land information based on spectral feature decision tree is proposed, and then the temporal spectral index features are analyzed. A method of extracting resident land information based on temporal spectral feature decision tree is proposed. On the basis of this method, temporal spectral index feature and depth learning technology are introduced into the identification and extraction of residential information at the same time. A method of extracting resident land information based on full convolution neural network based on temporal spectral features is proposed in this paper. Finally, the experimental results of the three methods are compared and analyzed, and a conclusion is drawn. The main conclusions of this paper are as follows: (1) the change of solar height angle not only affects the spectral size of the ground object, Even it has some influence on the spectral variation rate and the rate of change, and the spectral characteristics of different feature types vary with the solar height angle. (2) when the decision tree method is used, the spectral characteristics of the ground features vary with the solar height angle. (2) when the decision tree method is used, the spectral characteristics of the ground features vary with the solar height angle. Compared with the extraction of spectral features only, the time series spectral feature is used to extract the resident land information. The extraction accuracy is increased from 89.85% to 93.38%. (3) the extraction accuracy of resident land information based on temporal spectral features can be improved by using full convolution neural network, and the extraction precision is increased from 93.38% to 95.15%. In addition, the innovations of this thesis are as follows: (1) the relationship between temporal spectral features and solar height angle is introduced into the decision tree model, and compared with the resident extraction method which only makes use of spectral features, (2) combining the sequential spectral features with the full convolution neural network method in depth learning, the classification extraction accuracy is improved even more than other extraction methods which do not take into account the sequential spectral features or other extraction methods that do not use in-depth learning. (2) the sequential spectral features are combined with the full convolution neural network method in depth learning. Based on the temporal spectrum of GF-4 satellite remote sensing image, this paper studies the method of identification and extraction of land and land, and provides dynamic updating data for disaster reduction, disaster prevention, urbanization, urban fine management and land and resource management, and so on. It also provides technical and methodological support and demonstration guidance for the application of home-made high-grade series satellite data remote sensing products.
【學(xué)位授予單位】：中國(guó)科學(xué)院大學(xué)(中國(guó)科學(xué)院遙感與數(shù)字地球研究所)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：P237

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 ;《中國(guó)污染水體光譜特征》一書(shū)出版[J];遙感信息;2001年03期

2 祝昌漢,朱�？�,劉玉潔;地表光譜特征[J];氣象;1992年03期

3 包安明,吳中瑩;可見(jiàn)～近紅外波段礦物和巖石光譜特征——以新疆北疆部分地區(qū)巖石為例[J];干旱區(qū)地理;1993年03期

4 袁春瓊,胡列群;北疆一些水域光譜特征淺析[J];新疆氣象;1997年03期

5 楊柏林;巖礦光譜特征在遙感地質(zhì)找礦中的作用[J];地質(zhì)地球化學(xué);1989年05期

6 董秉宇;張建洪;;鉆石的輻射著色處理、色心及光譜特征(一)[J];國(guó)外非金屬礦與寶石;1990年04期

7 高來(lái)之,楊柏林;應(yīng)用于油氣資源遙感的近紅外石油物質(zhì)光譜特征研究[J];國(guó)土資源遙感;1991年04期

8 徐金鴻;;粵西不同母巖型紅土野外光譜特征[J];測(cè)繪科學(xué);2009年S2期

9 謝慧瑗,呂斯驊,金麗芳;幾種巖石的中紅外反射光譜特征[J];科學(xué)通報(bào);1983年20期

10 朱亞平;劉健文;白潔;;云的光譜和紋理特征統(tǒng)計(jì)分析[J];遙感技術(shù)與應(yīng)用;2006年01期

相關(guān)會(huì)議論文 前8條

1 張登榮;董傳萬(wàn);閻強(qiáng);鄧超;;浙東火山巖區(qū)巖墻可見(jiàn)光-近紅外遙感光譜特征[A];第十五屆全國(guó)遙感技術(shù)學(xué)術(shù)交流會(huì)論文摘要集[C];2005年

2 徐金鴻;;粵西不同母巖型紅土野外光譜特征[A];《測(cè)繪通報(bào)》測(cè)繪科學(xué)前沿技術(shù)論壇摘要集[C];2008年

3 吳德文;吳健生;周正武;張?jiān)品?;青海芒崖金多金屬成礦區(qū)巖石光譜特征及應(yīng)用[A];第十三屆全國(guó)遙感技術(shù)學(xué)術(shù)交流會(huì)論文摘要集[C];2001年

4 高占國(guó);張利權(quán);;鹽沼植被光譜特征的間接排序識(shí)別分析[A];第十五屆全國(guó)遙感技術(shù)學(xué)術(shù)交流會(huì)論文摘要集[C];2005年

5 王曉梅;張玉鈞;劉文清;夏慧;;基于光譜特征的植被遙感探測(cè)及應(yīng)用研究[A];第十五屆全國(guó)遙感技術(shù)學(xué)術(shù)交流會(huì)論文摘要集[C];2005年

6 林穎;徐衛(wèi)明;袁立銀;王建宇;;熱紅外高光譜非均勻性校正及光譜特征提取[A];第八屆成像光譜技術(shù)與應(yīng)用研討會(huì)暨交叉學(xué)科論壇文集[C];2010年

7 鄧書(shū)斌;陳秋錦;;植被光譜特征與植被指數(shù)綜述[A];第十七屆中國(guó)遙感大會(huì)摘要集[C];2010年

8 周寧;尹球;張鳳麗;朱迅;;服裝面料光譜特征初探[A];成像光譜技術(shù)與應(yīng)用研討會(huì)論文集[C];2002年

相關(guān)重要報(bào)紙文章 前1條

1 本報(bào)記者 沈俊霖;19個(gè)“電子眼”監(jiān)測(cè)膠州灣[N];青島日?qǐng)?bào);2011年

相關(guān)博士學(xué)位論文 前3條

1 劉丙新;基于高光譜特征的水上油膜提取與分析研究[D];大連海事大學(xué);2013年

2 高占國(guó);長(zhǎng)江口鹽沼植被的光譜特征研究[D];華東師范大學(xué);2006年

3 周廣柱;銅礦區(qū)植物光譜特征與信息提取[D];山東科技大學(xué);2007年

相關(guān)碩士學(xué)位論文 前10條

1 曲暢;基于GF-4衛(wèi)星影像時(shí)序光譜特征的居民地信息提取研究[D];中國(guó)科學(xué)院大學(xué)(中國(guó)科學(xué)院遙感與數(shù)字地球研究所);2017年

2 劉效棟;黃土臺(tái)塬區(qū)土壤有機(jī)質(zhì)高光譜特征及反演研究[D];西北農(nóng)林科技大學(xué);2015年

3 張宣宣;玉米鐵毒脅迫的光譜特征與葉綠素含量反演實(shí)驗(yàn)研究[D];東北大學(xué);2014年

4 張健;錫林郭勒典型草原植被光譜特征研究[D];內(nèi)蒙古大學(xué);2016年

5 劉璇;基于高光譜遙感圖像的植被光譜特征分析及含水量反演[D];哈爾濱工業(yè)大學(xué);2016年

6 王祥峰;基于光譜特征以及養(yǎng)分指示因子的土壤養(yǎng)分遙感監(jiān)測(cè)研究[D];遼寧工程技術(shù)大學(xué);2015年

7 趙思穎;稻田鎘污染高光譜響應(yīng)及其關(guān)系研究[D];江西師范大學(xué);2016年

8 孫勃巖;油菜的高光譜特征及其生理參數(shù)估算模型研究[D];西北農(nóng)林科技大學(xué);2017年

9 段瑞魯;科爾沁沙地典型沙丘植被光譜特征及其覆蓋變化分析[D];內(nèi)蒙古農(nóng)業(yè)大學(xué);2013年

10 張薈平;基于光譜特征不確定性的遙感影像分類研究[D];華中科技大學(xué);2013年

，

本文編號(hào)：2446454