發(fā)布時(shí)間：2019-01-02 12:59

【摘要】：圖像配準(zhǔn)的主要目的是為了實(shí)現(xiàn)同一目標(biāo)區(qū)域在不同時(shí)間、不同視角或不同傳感器獲得的圖像數(shù)據(jù)在空間位置上重合,圖像配準(zhǔn)問題是地理信息學(xué)、影像醫(yī)學(xué)、計(jì)算機(jī)視覺等眾多應(yīng)用領(lǐng)域中基礎(chǔ)性問題。對(duì)于完成衛(wèi)星遙感圖像之間的配準(zhǔn),得出的配準(zhǔn)信息對(duì)于完成目標(biāo)識(shí)別、圖像融合、場(chǎng)景重建等諸多應(yīng)用問題的實(shí)現(xiàn),有著至關(guān)重要的作用。在當(dāng)前海量的遙感圖像數(shù)據(jù)信息面前,傳統(tǒng)的人工選取圖像之間控制點(diǎn)實(shí)現(xiàn)遙感圖像配準(zhǔn)的方法已經(jīng)無法滿足實(shí)際應(yīng)用中對(duì)于數(shù)據(jù)實(shí)時(shí)性的要求,所以改善自動(dòng)化圖像配準(zhǔn)技術(shù),已成為圖像配準(zhǔn)領(lǐng)域中的研究重點(diǎn)方向。傳統(tǒng)的圖像配準(zhǔn)算法主要分為兩大類:基于圖像區(qū)域的配準(zhǔn)算法和基于圖像特征的配準(zhǔn)算法。本文主要采用了基于局部特征的配準(zhǔn)算法,并通過訓(xùn)練好的卷積神經(jīng)網(wǎng)絡(luò)來獲取控制點(diǎn)的特征表達(dá),以此來取得在圖像配準(zhǔn)的特征匹配階段有較好的正確匹配對(duì)的數(shù)量,進(jìn)而實(shí)現(xiàn)光學(xué)遙感圖像之間的配準(zhǔn),本文驗(yàn)證了提出方法的可行性,本文主要完成的工作具體有下列幾點(diǎn):1.總結(jié)了圖像配準(zhǔn)技術(shù)現(xiàn)階段的發(fā)展情況和傳統(tǒng)的圖像配準(zhǔn)流程,并對(duì)未來圖像配準(zhǔn)技術(shù)的發(fā)展方向做出了展望;2.介紹了圖像配準(zhǔn)以及卷積神經(jīng)網(wǎng)絡(luò)的理論知識(shí),并對(duì)卷積神經(jīng)網(wǎng)絡(luò)原理進(jìn)行了詳細(xì)的推導(dǎo)說明;3.采用最大穩(wěn)定極值區(qū)域(Maximally Stable Extremal Regions,MSERs)提取訓(xùn)練卷積神經(jīng)網(wǎng)絡(luò)所需要的特征樣本,并構(gòu)造合適的網(wǎng)絡(luò)結(jié)構(gòu)進(jìn)行網(wǎng)絡(luò)的訓(xùn)練。4.利用訓(xùn)練完成的卷積神經(jīng)網(wǎng)絡(luò)模型轉(zhuǎn)化待配準(zhǔn)圖像之間控制點(diǎn)的特征,并形成相應(yīng)的特征表達(dá),使用所得出的特征表達(dá)進(jìn)行特征匹配。最后在光學(xué)遙感圖像上進(jìn)行了此方法的模擬仿真實(shí)驗(yàn),并得出較好的圖像配準(zhǔn)效果。
[Abstract]:The main purpose of image registration is to realize the coincidence of image data obtained from the same target region at different time, different angle of view or different sensors in space. The problem of image registration is geographic informatics and image medicine. Basic problems in many fields of application, such as computer vision. For the registration of satellite remote sensing images, the registration information is very important to the realization of target recognition, image fusion, scene reconstruction and so on. In the face of the current massive remote sensing image data information, the traditional method of realizing remote sensing image registration by manually selecting control points between images can no longer meet the requirement of real-time data in practical applications. Therefore, improving the automatic image registration technology has become the focus of research in the field of image registration. Traditional image registration algorithms are mainly divided into two categories: image region-based registration algorithm and image feature-based registration algorithm. This paper mainly adopts the registration algorithm based on local features, and obtains the feature expression of the control points by the trained convolution neural network, so as to obtain the number of correct matching pairs in the feature matching stage of image registration. Then the registration of optical remote sensing images is realized. The feasibility of the proposed method is verified in this paper. The main work accomplished in this paper is as follows: 1. The current development of image registration technology and the traditional image registration process are summarized, and the future development direction of image registration technology is prospected. 2. The theoretical knowledge of image registration and convolution neural network is introduced, and the principle of convolution neural network is deduced in detail. The maximum stable extremum region (Maximally Stable Extremal Regions,MSERs) is used to extract the feature samples needed to train the convolutional neural network, and the appropriate network structure is constructed to train the network. 4. The convolution neural network model is used to transform the features of the control points between the images to be registered, and the corresponding feature expression is formed, and the obtained feature expression is used to match the features. Finally, the simulation experiment of this method is carried out on the optical remote sensing image, and a better image registration effect is obtained.
【學(xué)位授予單位】：南昌大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP751

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 龔丁禧;曹長(zhǎng)榮;;基于卷積神經(jīng)網(wǎng)絡(luò)的植物葉片分類[J];計(jì)算機(jī)與現(xiàn)代化;2014年04期

2 余凱;賈磊;陳雨強(qiáng);徐偉;;深度學(xué)習(xí)的昨天、今天和明天[J];計(jì)算機(jī)研究與發(fā)展;2013年09期

3 梁勇;程紅;孫文邦;王志強(qiáng);;圖像配準(zhǔn)方法研究[J];影像技術(shù);2010年04期

4 文貢堅(jiān);呂金建;王繼陽;;基于特征的高精度自動(dòng)圖像配準(zhǔn)方法[J];軟件學(xué)報(bào);2008年09期

5 王衛(wèi)東,俎棟林,包尚聯(lián),王澤華;基于邊緣提取的醫(yī)學(xué)圖像配準(zhǔn)方法[J];中國(guó)體視學(xué)與圖像分析;1998年04期

，

本文編號(hào)：2398517