本文選題：低空攝影測量　切入點(diǎn)：卷積神經(jīng)網(wǎng)絡(luò)　出處：《東華理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：DEM(Digital Elevation Model)可為數(shù)字城市建設(shè)、軍事、基礎(chǔ)測繪實(shí)施和災(zāi)后應(yīng)急救援等方面工作提供重要的數(shù)據(jù)支持。無人機(jī)低空攝影測量DEM生成技術(shù)是測繪地理信息數(shù)據(jù)處理研究熱點(diǎn)之一,低空攝影測量通過密集匹配可獲取數(shù)字地表模型(Digital Surface Model,DSM),相比衛(wèi)星攝影測量,其獲取的地表細(xì)節(jié)信息更為豐富突出,但也為DEM自動(dòng)生成帶來較大困難,解決此類問題常用方法主要包括人工后處理和DSM濾波方法。但人工后處理耗時(shí)、自動(dòng)化程度低,而已有濾波方法難以針對性過濾建筑物、樹林等地物高程信息,對其他區(qū)域也會(huì)進(jìn)行平抑,具有一定盲目性。因此,自動(dòng)識別建筑物、樹林等目標(biāo)區(qū)并進(jìn)行DEM修補(bǔ),對DEM自動(dòng)生成具有一定的價(jià)值。近年來,以深度學(xué)習(xí)為代表的人工智能算法在遙感目標(biāo)識別與分類中表現(xiàn)了優(yōu)異的性能,本文采用卷積神經(jīng)網(wǎng)絡(luò)(Convolution Neural Network,CNN),利用構(gòu)建的CNN低空遙感分類模型識別建筑物、樹林等目標(biāo)區(qū),通過抗差徑向神經(jīng)網(wǎng)絡(luò)高程曲面擬合法修補(bǔ)目標(biāo)區(qū)高程,旨在實(shí)現(xiàn)由無人機(jī)低空遙感數(shù)據(jù)自動(dòng)化修補(bǔ)DEM。針對上述內(nèi)容,本文主要開展以下研究工作:(1)基于卷積神經(jīng)網(wǎng)絡(luò)原理,構(gòu)建CNN低空遙感分類模型,并測試該模型對房屋、植被、道路等非地面要素的分類精度,取得較好效果,驗(yàn)證了該CNN模型的有效性。(2)針對DSM中含有大量非地面要素的點(diǎn)云數(shù)據(jù),利用構(gòu)建的CNN低空遙感分類模型對DSM數(shù)據(jù)進(jìn)行判別,提取非地面要素構(gòu)建DEM修補(bǔ)目標(biāo)區(qū),剔除修補(bǔ)目標(biāo)區(qū)高程點(diǎn),并利用目標(biāo)區(qū)鄰近高程點(diǎn)擬合其高程。采用高差能量衰減函數(shù)迭代搜索修補(bǔ)目標(biāo)區(qū)鄰近高程點(diǎn)的選取區(qū)間,同時(shí)顧及鄰近高程點(diǎn)的粗差,通過抗差徑向神經(jīng)網(wǎng)絡(luò)高程曲面擬合法實(shí)現(xiàn)修補(bǔ)目標(biāo)區(qū)的高程曲面擬合。(3)采用DSM濾波以及人工后處理方法與本文研究方法進(jìn)行對比實(shí)驗(yàn),分別生成DEM、三維地形、等高線,同時(shí)選取均勻分布的檢核點(diǎn)進(jìn)行精度比較,結(jié)果表明本文方法殘差較小且外符合精度與人工后處理方法接近,驗(yàn)證了本文方法的有效性。(4)采用克里金、IDW、RBF、局部多項(xiàng)式四種插值算法與本文研究方法進(jìn)行對比實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明DEM精度受建筑物、樹林等非地面要素干擾較大,本文方法精度高于克里金、IDW、RBF、局部多項(xiàng)式插值算法,適用于低空攝影測量DEM自動(dòng)修補(bǔ),修補(bǔ)后的DEM能準(zhǔn)確表達(dá)地形地貌。
[Abstract]:DEM (Digital Elevation Model) for the construction of digital city, the military, in support of the implementation of basic surveying and mapping and post disaster emergency rescue and other aspects of the work. The UAV low altitude photogrammetry DEM generation technology of Surveying and mapping geographic information data processing is one of research hotspots, low altitude photogrammetry through dense matching can get a digital surface model (Digital Surface Model, DSM), compared with satellite photogrammetry, the surface details of its acquisition more prominent, but also brings great difficulties for the automatic generation of DEM, commonly used methods to solve these problems mainly include manual postprocessing and DSM filtering methods. But the manual postprocessing time-consuming, low degree of automation, it is difficult to filter for filtering buildings, trees and other surface elevation information, will stabilize to other regions, have certain blindness. Therefore, the automatic recognition of buildings, trees and target area And DEM repair, which has a certain value for the automatic generation of DEM. In recent years, with the deep learning artificial intelligence algorithm represented in remote sensing target recognition and classification showed excellent performance, this paper adopts convolutional neural network (Convolution Neural Network, CNN), using CNN low altitude remote sensing classification model to identify the construction of buildings, trees as the target area by RBF neural network robust elevation surface fitting elevation of legal repair targets, to achieve by the UAV low altitude remote sensing data automatic repair DEM. in view of the above content, this paper mainly carry out the work to study: (1) the principle of convolutional neural network based on the construction of low altitude remote sensing classification CNN model, and test the model of vegetation housing, roads, the classification accuracy of non ground elements, to achieve better results, verify the validity of the CNN model. (2) for the DSM contains a large number of non ground point cloud elements The data, to identify the data using the DSM CNN model of low altitude remote sensing classification, extraction of non ground elements to build DEM repair the target area, excluding the repair target elevation point, and use the fitting target area adjacent elevation point elevation. The attenuation function iterative search repair interval selection target area adjacent elevation point by high energy, at the same time the gross error adjacent elevation point, through the robust neural network elevation surface fitting method elevation surface fitting repair target area. (3) using DSM filtering and processing method of artificial and the research methods of this paper were compared respectively to generate DEM, 3D terrain, contour, and select the uniform distribution of check point accuracy comparison results show that the method error is small and the outer precision and artificial postprocessing method to verify the validity of this method. (4) by Riggin IDW, RBF, G, Bureau Part four polynomial interpolation algorithm and the research method of comparative experiments, the experimental results show that the accuracy of DEM by the buildings, trees and other non ground elements of noise, the accuracy of this method is higher than that of IDW, RBF, Kriging interpolation, local polynomial interpolation algorithm, suitable for low altitude photogrammetry DEM Auto repair, repair after DEM can accurately express the topography.

【學(xué)位授予單位】：東華理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：P208;P231

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 何海清;游琦;陳曉勇;;卷積神經(jīng)網(wǎng)絡(luò)支持下的低空攝影測量DEM修補(bǔ)[J];遙感信息;2017年01期

2 陳傳法;劉鳳英;閆長青;戴洪磊;郭金運(yùn);劉國林;;DEM建模的多面函數(shù)Huber抗差算法[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2016年06期

3 曹林林;李海濤;韓顏順;余凡;顧海燕;;卷積神經(jīng)網(wǎng)絡(luò)在高分遙感影像分類中的應(yīng)用[J];測繪科學(xué);2016年09期

4 盧宏濤;張秦川;;深度卷積神經(jīng)網(wǎng)絡(luò)在計(jì)算機(jī)視覺中的應(yīng)用研究綜述[J];數(shù)據(jù)采集與處理;2016年01期

5 焦李成;楊淑媛;劉芳;王士剛;馮志璽;;神經(jīng)網(wǎng)絡(luò)七十年:回顧與展望[J];計(jì)算機(jī)學(xué)報(bào);2016年08期

6 張敏;金龍旭;李國寧;武奕楠;韓雙麗;;基于直線特征的攝像機(jī)鏡頭畸變標(biāo)定方法[J];光學(xué)學(xué)報(bào);2015年06期

7 何海清;黃聲享;陳婷;;一種顧及粗差的徑向神經(jīng)網(wǎng)絡(luò)高程曲面擬合法[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2015年04期

8 余永維;殷國富;殷鷹;杜柳青;;基于深度學(xué)習(xí)網(wǎng)絡(luò)的射線圖像缺陷識別方法[J];儀器儀表學(xué)報(bào);2014年09期

9 湯國安;;我國數(shù)字高程模型與數(shù)字地形分析研究進(jìn)展[J];地理學(xué)報(bào);2014年09期

10 呂國豪;羅四維;黃雅平;蔣欣蘭;;基于卷積神經(jīng)網(wǎng)絡(luò)的正則化方法[J];計(jì)算機(jī)研究與發(fā)展;2014年09期

相關(guān)博士學(xué)位論文 前5條

1 曹輝;智能空中三角測量中若干關(guān)鍵技術(shù)的研究[D];武漢大學(xué);2013年

2 何海清;低空攝影測量航帶重構(gòu)及數(shù)據(jù)處理方法研究[D];武漢大學(xué);2013年

3 許彪;基于航空影像的真正射影像制作關(guān)鍵技術(shù)研究[D];武漢大學(xué);2012年

4 張錦明;DEM插值算法適應(yīng)性研究[D];解放軍信息工程大學(xué);2012年

5 盧華興;DEM誤差模型研究[D];南京師范大學(xué);2008年

相關(guān)碩士學(xué)位論文 前2條

1 凡保磊;卷積神經(jīng)網(wǎng)絡(luò)的并行化研究[D];鄭州大學(xué);2013年

2 魏月興;徑向基插值近似方法理論與應(yīng)用研究[D];國防科學(xué)技術(shù)大學(xué);2009年

，

本文編號：1622460