本文選題：高鐵沿線隱患 + 場景解譯��； 參考：《西南交通大學(xué)》2017年碩士論文

【摘要】：高速鐵路沿線地理環(huán)境復(fù)雜,存在諸多安全隱患,尤其是沿線的房屋、工廠等非法建筑嚴(yán)重影響到高鐵的安全運營。因此,必須及時對高鐵沿線建筑隱患進行排查。傳統(tǒng)的人工實地勘察檢測建筑隱患的方法費時費力、效率低下,難以對整個高鐵網(wǎng)絡(luò)進行有效的監(jiān)控。高分辨率遙感技術(shù)具有實時性、周期性等技術(shù)優(yōu)勢,為快速、客觀、動態(tài)地監(jiān)測高鐵沿線建筑隱患提供了有效的技術(shù)手段。高分辨率遙感影像地物細(xì)節(jié)信息十分豐富,但是也存在大量"同物異譜"和"異物同譜"的現(xiàn)象,導(dǎo)致傳統(tǒng)的基于像素提取建筑方法精度較低。面向?qū)ο蠓椒ㄓ捎陬櫦傲讼袼刂g的空間關(guān)系,在一定程度上提高了高分辨率遙感影像建筑物識別的精度,但是確定最優(yōu)分割尺度往往比較困難。此外,這兩種方法提取建筑時往往基于圖像的底層視覺特征分析,并沒有建立在圖像所描述的高層次語義特征之上,因此,存在明顯的語義鴻溝,影響建筑物識別的精度。為了突破這一限制,需要從更高層次的場景層次去理解高分辨率遙感影像。本文選取京滬高鐵宿州-蚌埠某段的Google Earth影像作為研究數(shù)據(jù)。在場景解譯框架下,本文首先建立高鐵沿線影像塊樣本庫,然后將高鐵沿線影像劃分為重疊的影像塊。將影像塊看作文檔,通過視覺詞袋模型和潛在狄利克雷分布主題模型分別得到影像塊的視覺單詞直方圖表示和潛在的語義主題混合比例信息,輸入到SVM分類器得到影像塊的類別,最后通過類別投票法確定每個像素的類別,從而實現(xiàn)建筑物隱患的自動識別;將影像塊輸入到經(jīng)過訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò),通過卷積、池化、全連接操作得到全連接層,輸入到Softmax得到每個影像塊的類別概率分布,最后通過等權(quán)平均的方式得到每個像素的類別概率分布,取概率最大所屬類別作為該像素的類別,從而實現(xiàn)建筑物隱患的提取。經(jīng)過實驗分析,得到以下結(jié)論:經(jīng)過實驗分析,得到以下結(jié)論:(1)相比于傳統(tǒng)的基于像素和面向?qū)ο笫褂玫讓犹卣鞯慕ㄖ[患識別方法,基于場景解譯方法能夠顯著提升結(jié)果緊湊性和完整性,總體精度和生產(chǎn)者精度最高均可達91%,kappa系數(shù)可達0.71,與地面真實值較為接近;(2)場景解譯框架下各方法中,卷積神經(jīng)網(wǎng)絡(luò)方法通過自主學(xué)習(xí),避免了視覺詞袋模型和主題模型人工設(shè)計特征的局限性與盲目性,目視評價與指標(biāo)評價上表現(xiàn)最優(yōu)。
[Abstract]:Because of the complex geographical environment along the high-speed railway, there are many hidden dangers in safety, especially the illegal buildings such as houses and factories along the high-speed railway seriously affect the safe operation of high-speed railway. Therefore, must carry on the investigation in time to the construction hidden danger along the high-speed line. The traditional manual investigation and detection method of building hidden trouble is time-consuming and inefficient, so it is difficult to monitor the whole high-speed railway network effectively. High-resolution remote sensing technology has the advantages of real-time and periodicity, which provides an effective technical means for rapid, objective and dynamic monitoring of building hidden trouble along high-speed railway line. High resolution remote sensing images are rich in detailed information of features, but there are also a large number of "isospectral" and "foreign body isospectral" phenomena, which leads to the low accuracy of traditional methods of pixel extraction and construction. Due to the spatial relationship between pixels, the object-oriented method improves the accuracy of building recognition in high-resolution remote sensing images to a certain extent, but it is often difficult to determine the optimal segmentation scale. In addition, these two methods are often based on the analysis of the underlying visual features of the image, and are not based on the high-level semantic features described by the image. Therefore, there is a clear semantic gap, which affects the accuracy of building recognition. In order to overcome this limitation, high resolution remote sensing images need to be understood at a higher level. In this paper, the Google Earth image of Suzhou-Bengbu section of Beijing-Shanghai high-speed train is selected as the research data. Under the frame of scene interpretation, this paper first establishes the sample database of high-speed railway image blocks, and then divides the high-speed railway images into overlapping image blocks. The image block is regarded as a document, and the visual word histogram representation and the potential semantic topic mixed proportion information are obtained by the visual word bag model and the potential Drickley distribution theme model, respectively. Input into the SVM classifier to get the classification of the image block, finally determine the category of each pixel through the class voting method, thus realize the automatic identification of the hidden trouble of the building; input the image block to the trained convolution neural network, through the convolution, pool, pool, The full connection layer is obtained by the full join operation, and the class probability distribution of each image block is obtained by input into Softmax. Finally, the class probability distribution of each pixel is obtained by equal weight average, and the category belonging to the maximum probability is taken as the class of the pixel. In order to achieve the extraction of hidden dangers of buildings. Through the experimental analysis, the following conclusions are obtained: through the experimental analysis, the following conclusions are obtained: compared with the traditional method based on pixel and object-oriented using the bottom feature of building hidden trouble recognition, Based on the method of scene interpretation, the compactness and integrality of the result can be significantly improved. The highest overall precision and producer precision can reach 91kappa coefficient of 0.71, which is close to the real value of ground level. The convolution neural network method avoids the limitation and blindness of the artificial design features of visual word bag model and theme model through autonomous learning. The visual evaluation and index evaluation are the best.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：U298;TP751

【參考文獻】

相關(guān)期刊論文 前10條

1 何小飛;鄒崢嶸;陶超;張佳興;;聯(lián)合顯著性和多層卷積神經(jīng)網(wǎng)絡(luò)的高分影像場景分類[J];測繪學(xué)報;2016年09期

2 許夙暉;慕曉冬;趙鵬;馬驥;;利用多尺度特征與深度網(wǎng)絡(luò)對遙感影像進行場景分類[J];測繪學(xué)報;2016年07期

3 李德仁;童慶禧;李榮興;龔健雅;張良培;;高分辨率對地觀測的若干前沿科學(xué)問題[J];中國科學(xué):地球科學(xué);2012年06期

4 徐侃;楊文;陳麗君;孫洪;;利用主題模型的遙感圖像場景分類[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2011年05期

5 譚衢霖;;高分辨率多光譜影像城區(qū)建筑物提取研究[J];測繪學(xué)報;2010年06期

6 陳杰;鄧敏;肖鵬峰;楊敏華;梅小明;;粗糙集高分辨率遙感影像面向?qū)ο蠓诸怺J];遙感學(xué)報;2010年06期

7 林先成;李永樹;;面向?qū)ο蟮某啥计皆叻直媛蔬b感影像分類研究[J];西南交通大學(xué)學(xué)報;2010年03期

8 陳云浩;馮通;史培軍;王今飛;;基于面向?qū)ο蠛鸵?guī)則的遙感影像分類研究[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2006年04期

9 許磊;李朝峰;楊蒙召;;SVM結(jié)合模糊方法在遙感圖像分類中的應(yīng)用[J];計算機工程與應(yīng)用;2005年36期

10 李德仁;論21世紀(jì)遙感與GIS的發(fā)展[J];武漢大學(xué)學(xué)報(信息科學(xué)版);2003年02期

，

本文編號：1841402