本文選題：自動(dòng)識(shí)別 + 遙感圖像��； 參考：《南京航空航天大學(xué)》2017年碩士論文

【摘要】：伴隨著計(jì)算機(jī)視覺技術(shù)的發(fā)展,遙感圖像中的目標(biāo)自動(dòng)識(shí)別已經(jīng)成為研究的熱點(diǎn)和重點(diǎn)。橋梁作為典型且重要的人工建筑,是交通運(yùn)輸線路的咽喉。對采集圖像中的橋梁進(jìn)行有效識(shí)別,在民用及軍事上都有著廣泛需求。本文以復(fù)雜場景下的可見光遙感圖像中橋梁目標(biāo)的自動(dòng)識(shí)別作為研究背景,針對河流的自動(dòng)提取和河流上橋梁的定位等問題進(jìn)行了研究。根據(jù)復(fù)雜場景下水上橋梁圖像的特點(diǎn):不同圖像中河流差異較大,水面可能平靜,分布均勻,也可能由于波浪和水體渾濁造成河流紋理豐富,分布不均勻。復(fù)雜場景下圖像的背景區(qū)域也多樣性,可能包含多種自然景物、農(nóng)作物或人工建筑,如林地、耕地和居民地等,使得背景中包含多種形式的紋理。在此基礎(chǔ)上本文建構(gòu)了一套完整的水上橋梁自動(dòng)識(shí)別系統(tǒng)。主要研究內(nèi)容如下:(1)復(fù)雜場景下的橋梁圖像,河流雖然呈現(xiàn)出不同的形式,其灰度值或高或低,分布或均勻或雜亂。但河流區(qū)域之間的顏色相似度較高,河流區(qū)域的顏色相比背景區(qū)域的顏色差異較大。根據(jù)顏色特征相似度,本文提出了K均值聚類與Harris角點(diǎn)相結(jié)合的無監(jiān)督分割法實(shí)現(xiàn)河流的自動(dòng)提取。(2)針對更復(fù)雜的橋梁圖像,即河流區(qū)域內(nèi),部分顏色差異較大,河流顏色無明顯規(guī)律的情況,K均值聚類與Harris角點(diǎn)相結(jié)合的方法不能提取出較為完整的河流,但可以提取出河流區(qū)域中的部分樣本。利用這部分樣本提取出能代表本張圖像中的河流區(qū)域的顏色和紋理特征,進(jìn)行學(xué)習(xí),采用自監(jiān)督分割方法,對圖像中的所有像素點(diǎn)分類,分割出完整的河流區(qū)域。(3)對分割出的河流進(jìn)行形態(tài)學(xué)操作和干擾區(qū)域的剔除,得到較為完整的河流輪廓。對河流二值圖像膨脹腐蝕,填補(bǔ)截?cái)辔恢玫玫竭B通的河流二值圖,與原來的河流二值圖像作差,提取出疑似橋梁的截?cái)鄥^(qū)域。利用河流骨架與橋梁相交的特征剔除部分虛假橋梁,再根據(jù)橋梁拐點(diǎn)的特征,驗(yàn)證真實(shí)橋梁的存在性,完成真實(shí)橋梁的獲取,將驗(yàn)證后的橋梁對應(yīng)在原圖像的位置進(jìn)行標(biāo)記,從而實(shí)現(xiàn)橋梁定位。(4)本文提出的橋梁自動(dòng)識(shí)別方法以Visual Studio 2010為開發(fā)平臺(tái),并結(jié)合OpenCV開源視覺庫實(shí)現(xiàn)了該系統(tǒng)的開發(fā)。實(shí)驗(yàn)表明,該系統(tǒng)能夠自動(dòng)識(shí)別出高空水上橋梁圖像中的橋梁目標(biāo),并具有一定的適用性。
[Abstract]:With the development of computer vision technology, automatic target recognition in remote sensing images has become a hot spot and focus. As a typical and important artificial building, bridge is the throat of transportation line. It is widely needed in civil and military fields to identify bridges in image collection. In this paper, the automatic recognition of bridge targets in visible light remote sensing images of complex scenes is used as the research background, and the automatic extraction of rivers and the location of bridges on rivers are studied in this paper. According to the characteristics of bridge image in the water of complex scene: the river is different in different images, the water surface may be calm and distributed evenly, or the river texture may be rich and uneven due to the wave and water turbidity. The background areas of the images in complex scenes are also diverse and may include many natural scenes crops or artificial buildings such as forest farmland and inhabitant land which make the background contain many kinds of textures. On the basis of this, this paper constructs a set of complete automatic recognition system of water bridge. The main contents of this study are as follows: (1) Bridge images in complex scenes. Although rivers show different forms, their gray values are high or low, and their distribution is uniform or chaotic. However, the color similarity of river region is higher, and the color of river region is more different than that of background region. According to the similarity of color features, an unsupervised segmentation method based on K-means clustering and Harris corner is proposed to automatically extract river. If there is no obvious rule of river color, the method of K-means clustering combined with Harris corner can not extract more complete river, but can extract some samples from river region. Using this part of the sample to extract the color and texture features which can represent the river region in this image, to learn, to use the self-supervised segmentation method, to classify all the pixels in the image. The whole river area is segmented. (3) the whole river contour is obtained by morphological operation and elimination of the interference area of the segmented river. When the river binary image is dilated and corroded, the connected river binary image is obtained by filling the truncation position, which is different from the original river binary image, and the truncated area of the suspected bridge is extracted. By using the feature of river skeleton intersecting with bridge, some false bridges are eliminated, then the existence of real bridge is verified according to the characteristics of bridge inflection point, and the acquisition of real bridge is completed, and the verified bridge is marked corresponding to the position of the original image. The bridge automatic recognition method proposed in this paper is developed on the platform of Visual Studio 2010 and the open source vision library of OpenCV is used to realize the development of the system. The experimental results show that the system can automatically identify the bridge targets in the image of high altitude water bridge, and it is applicable to some extent.
【學(xué)位授予單位】：南京航空航天大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳愛軍;;大幅面衛(wèi)星遙感圖像中橋梁識(shí)別算法[J];計(jì)算機(jī)仿真;2014年06期

2 馬瑜;梁慧琳;張艷寧;李韻;徐爽;;基于圖像顏色紋理的均值漂移分割算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2013年05期

3 高鳳嬌;;基于環(huán)境要素的枯水期水上橋梁目標(biāo)的定位方法[J];電子技術(shù)應(yīng)用;2013年02期

4 章錦文;宋小春;趙廣州;陳仁;;橋梁目標(biāo)識(shí)別方法綜述[J];紅外與激光工程;2012年12期

5 于素芬;;一種用于橋梁識(shí)別的水域分割提取方法[J];電光與控制;2011年08期

6 吳定海;張培林;任國全;陳非;;基于支持向量的單類分類方法綜述[J];計(jì)算機(jī)工程;2011年05期

7 彭碧發(fā);譚毅華;陶超;田金文;;從高分辨率遙感圖像中自動(dòng)識(shí)別水上橋梁[J];應(yīng)用科學(xué)學(xué)報(bào);2010年04期

8 蔡飛;涂丹;;可見光圖像人造目標(biāo)檢測技術(shù)綜述[J];計(jì)算機(jī)應(yīng)用研究;2010年07期

9 雷寶權(quán);楊麗華;程詠梅;趙春暉;吳燕茹;;基于SVM與顏色/紋理組合特征的景物識(shí)別算法[J];計(jì)算機(jī)科學(xué);2009年10期

10 秦劍;李林;李紹明;王龍鶴;時(shí)振通;;基于梯度的圖像分割新方法[J];計(jì)算機(jī)應(yīng)用;2009年08期

相關(guān)博士學(xué)位論文 前2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

2 陳愛軍;典型人造目標(biāo)自動(dòng)識(shí)別算法研究[D];哈爾濱工業(yè)大學(xué);2008年

相關(guān)碩士學(xué)位論文 前3條

1 曾蕾;基于航天可見光遙感圖像的艦船目標(biāo)檢測和速度估算方法[D];西安電子科技大學(xué);2014年

2 薄麗萍;橋梁目標(biāo)識(shí)別的研究與實(shí)現(xiàn)[D];中北大學(xué);2010年

3 方曉芙;遙感圖像中戰(zhàn)略目標(biāo)識(shí)別方法研究[D];西北工業(yè)大學(xué);2004年

，

本文編號(hào)：1780317