本文關(guān)鍵詞： 視差圖像拼接 多層次 特征提取 特征匹配 特征分塊　出處：《西南交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：針對(duì)現(xiàn)有的視差圖像拼接算法中單應(yīng)性矩陣不具有全局性、計(jì)算量大,圖像匹配精度不高且拼接結(jié)果有重影和結(jié)構(gòu)扭曲的問題,提出了基于多層次特征提取與匹配的視差圖像拼接算法。本文用基于特征分塊的視差圖像拼接算法提高計(jì)算效率,用多層次特征提取與匹配模型提高匹配精度,用視差圖像局部?jī)?yōu)化模型消除重影和形狀扭曲。主要研究?jī)?nèi)容如下:1)基于特征分塊的視差圖像拼接算法。首先,用圖割算法將參照?qǐng)D像I1和目標(biāo)圖像I2分割成若干個(gè)具有獨(dú)特性質(zhì)的圖像塊,并將圖像塊編號(hào);然后,用特征分塊法確定參照?qǐng)D像與目標(biāo)圖像之間的特征匹配圖像塊;最后,用特征分塊法計(jì)算全局單應(yīng)性矩陣Hi。實(shí)驗(yàn)結(jié)果表明,用本文提出的特征分塊算法可以快速確定圖像之間的重疊區(qū)域和非重疊區(qū)域,保證了單應(yīng)性矩陣的全局性,減少了計(jì)算單應(yīng)性矩陣的迭代次數(shù),提高了算法的計(jì)算效率。2)改進(jìn)了多層次匹配框架,設(shè)計(jì)了一種多層次特征提取與匹配模型,對(duì)視差圖像進(jìn)行匹配。首先,搭建多層次特征提取和匹配框架;然后,進(jìn)行多層次特征提取;最后,進(jìn)行多層次特征匹配。在進(jìn)行多層次特征提取時(shí),從高分辨率層到結(jié)構(gòu)層逐層進(jìn)行特征匯聚,可以保證提取特征的準(zhǔn)確性。在進(jìn)行多層次特征匹配時(shí)按照"由粗到精"的策略用結(jié)構(gòu)層的匹配結(jié)果指導(dǎo)高分辨率層的匹配,這樣可以提高匹配的精度和速度。通過對(duì)比實(shí)驗(yàn)可以發(fā)現(xiàn)本文的多層次特征提取及匹配模型可以提高匹配的精度。3)設(shè)計(jì)了一種視差圖像局部?jī)?yōu)化模型,消除視差圖像拼接過程中產(chǎn)生的重影和形狀扭曲。首先,采用本文提出的"結(jié)構(gòu)+紋理"的方法找出最優(yōu)全局單應(yīng)性矩陣H,用H對(duì)目標(biāo)圖像I2進(jìn)行變換得到預(yù)配準(zhǔn)圖像I2;然后,本文在現(xiàn)有的位置變化約束和相似變換約束的基礎(chǔ)上加入塊鏈接約束,對(duì)I2的重疊區(qū)域進(jìn)行局部?jī)?yōu)化,得到局部修正后的目標(biāo)圖像I2;最后,用雙線性插值法進(jìn)行圖像融合得到最終的拼接圖像。對(duì)比實(shí)驗(yàn)證明本文算法可以較好消除重影和形狀扭曲,提高了視差圖像拼接的質(zhì)量。
[Abstract]:In the existing parallax image stitching algorithms, the monoclinic matrix is not global, the computation is large, the image matching accuracy is not high, and the stitching result has the problems of double shadow and structure distortion. A parallax image mosaic algorithm based on multi-level feature extraction and matching is proposed. In this paper, the parallax image mosaic algorithm based on feature block is used to improve the computational efficiency, and the multi-level feature extraction and matching model is used to improve the matching accuracy. The partial optimization model of parallax image is used to eliminate double shadow and shape distortion. The main contents of this paper are as follows: 1) Parallax image mosaic algorithm based on feature partitioning. First of all. The reference image I1 and the target image I2 are divided into a number of unique image blocks by using the graph cutting algorithm, and the image blocks are numbered. Then, the feature matching image block between the reference image and the target image is determined by the feature block method. Finally, the feature block method is used to calculate the global homotropic matrix Hi.The experimental results show that the proposed feature block algorithm can quickly determine the overlapped and non-overlapping regions between images. The global property of homotropic matrix is guaranteed, the iteration times of calculating homotropic matrix are reduced, and the computational efficiency of the algorithm is improved. 2) the multi-level matching framework is improved. A multi-level feature extraction and matching model is designed to match parallax image. Firstly, a multi-level feature extraction and matching framework is built. Then, multi-level feature extraction is carried out. Finally, multi-level feature matching is carried out. In the process of multi-level feature extraction, features converge from high-resolution layer to structure layer. It can ensure the accuracy of feature extraction. According to the strategy of "from coarse to fine", the matching result of structure layer is used to guide the matching of high resolution layer in multi-level feature matching. Through comparison experiments, we can find that the multi-level feature extraction and matching model can improve the matching accuracy. 3) A parallax image local optimization model is designed. The double shadow and shape distortion generated in parallax image stitching are eliminated. Firstly, the "structure texture" method proposed in this paper is used to find out the optimal global homotropic matrix H. The target image I2 is transformed by H to get the pre-registered image I2. Then, based on the existing position change constraints and similarity transformation constraints, block link constraints are added to optimize the overlapped region of I2 and obtain the locally modified target image I2. Finally, the bilinear interpolation method is used to fuse the image to obtain the final stitched image, and the contrast experiment shows that the algorithm can eliminate the double image and shape distortion, and improve the quality of parallax image mosaic.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳潔;高志強(qiáng);密保秀;陳會(huì);;引入極線約束的SURF特征匹配算法[J];中國(guó)圖象圖形學(xué)報(bào);2016年08期

2 黃靜;;低重疊率和弱紋理圖像的快速拼接算法[J];湖南科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年02期

3 李玉峰;李廣澤;谷紹湖;龍科慧;;基于區(qū)域分塊與尺度不變特征變換的圖像拼接算法[J];光學(xué)精密工程;2016年05期

4 王忠美;楊曉梅;顧行發(fā);周成虎;;投影相似變換的無人機(jī)影像拼接[J];測(cè)繪科學(xué);2016年09期

5 趙陽陽;;基于大視差圖像中目標(biāo)物體的拼接[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2015年32期

6 孫金亮;姚睿;周勇;陳岱;;形狀與內(nèi)容保護(hù)的多攝像機(jī)視頻融合方法[J];南京大學(xué)學(xué)報(bào)(自然科學(xué));2015年04期

7 王燦進(jìn);孫濤;陳娟;;局部不變特征匹配的并行加速技術(shù)研究[J];液晶與顯示;2014年02期

8 杜京義;胡益民;劉宇程;;基于區(qū)域分塊的SIFT圖像匹配技術(shù)研究與實(shí)現(xiàn)[J];光電工程;2013年08期

9 劉志文;劉定生;劉鵬;;應(yīng)用尺度不變特征變換的多源遙感影像特征點(diǎn)匹配[J];光學(xué)精密工程;2013年08期

10 劉君;徐來明;左小女;;一種基于互信息與梯度的圖像精確配準(zhǔn)方法[J];南昌大學(xué)學(xué)報(bào)(工科版);2012年04期

，

本文編號(hào)：1476988