本文選題：圖像拼接 + SIFT��； 參考：《西北農(nóng)林科技大學(xué)》2017年碩士論文

【摘要】：基于特征的圖像拼接技術(shù)因其能夠更加充分的利用圖像中的信息,使圖像間的配準(zhǔn)更加精確,已成為圖像拼接技術(shù)中的主要研究方向。在特征的類型的選取上,尺度不變特征變換(Scale-invariant feature transform,簡稱SIFT)算法因其獨(dú)特性好,產(chǎn)生數(shù)量多,魯棒性強(qiáng)、可擴(kuò)展性好等優(yōu)點(diǎn),而成為眾多研究中主要選取的特征類型。本論文針對(duì)實(shí)驗(yàn)中使用傳統(tǒng)SIFT算法進(jìn)行作物圖像拼接時(shí),對(duì)圖像非重疊區(qū)域部分提取特征點(diǎn)過多以及處理高分辨率作物圖像時(shí)速度緩慢的問題,從拼接過程中的局部和整體這兩方面各提出了一種新的改進(jìn)算法策略,主要的研究內(nèi)容如下。(1)從輸入的6張農(nóng)作物圖像中檢測SIFT特征點(diǎn),每兩張為一組利用基于k-d樹的BBF算法進(jìn)行特征點(diǎn)匹配,建立待拼接農(nóng)作物圖像間的匹配關(guān)系;然后,使用RANSAC算法選出正確匹配的特征點(diǎn),計(jì)算出每組待拼接圖像間的變換矩陣,并利用圖像融合技術(shù)實(shí)現(xiàn)每組作物圖像間的拼接;最后,將前兩組的拼接結(jié)果與最后一組拼接,完成最終6張作物圖像的拼接。通過編程實(shí)現(xiàn)及實(shí)驗(yàn)測試,針對(duì)所拍攝農(nóng)作物圖像中,主要景物間存在較為明顯的像素對(duì)比度的特點(diǎn),提出了一種適用于作物圖像的快速特征點(diǎn)匹配方法。該方法通過提高圖像中像素對(duì)比度的閾值,實(shí)現(xiàn)對(duì)圖像中主要景物的特征提取,減少對(duì)圖像中無用特征點(diǎn)的提取。實(shí)驗(yàn)表明,所提方法在處理農(nóng)作物圖像時(shí),匹配精度相比較于使用傳統(tǒng)的SIFT算法提升了10%左右,且速度也提升了1倍。(2)針對(duì)使用傳統(tǒng)的SIFT算法進(jìn)行農(nóng)作物圖像拼接時(shí)所存在的兩個(gè)問題:(a)待拼接圖像中非重復(fù)區(qū)域的特征點(diǎn)并不參與最終圖像拼接的計(jì)算,且對(duì)于高分辨率的農(nóng)作物圖像來說更是增加了大量不必要的計(jì)算,占用了大量的內(nèi)存,造成了時(shí)間上的嚴(yán)重浪費(fèi)。(b)農(nóng)作物圖像中重復(fù)的景物,很容易在特征點(diǎn)匹配階段形成錯(cuò)誤的匹配點(diǎn)對(duì),增加最終變換矩陣的計(jì)算時(shí)間。本文提出了一種處理高分辨率農(nóng)作物圖像的拼接策略,該策略先降低圖像的分辨率,求出兩幅待拼接圖像間的大致重疊區(qū)域,再逐步對(duì)重疊區(qū)域求精,實(shí)現(xiàn)只對(duì)重疊區(qū)域的特征點(diǎn)進(jìn)行檢測,從而在一定程度上避免上述的兩個(gè)問題,不僅提高了高分辨率農(nóng)作物圖像拼接的速度,而且提升了圖像配準(zhǔn)的精度。實(shí)驗(yàn)表明,該策略相比較于傳統(tǒng)的SIFT算法在匹配精度上提升了20%左右。
[Abstract]:Feature based image mosaic technology has become the main research direction of image mosaic technology because it can make full use of the information in the image and make the registration between images more accurate.In the selection of feature types, Scale-invariant feature transform (sift) algorithm has become the main feature type in many researches because of its advantages of good uniqueness, large quantity, strong robustness and good expansibility.In this paper, we aim at the problem of too many feature points in the non-overlapping region and the slow speed of processing high-resolution crop images when we use the traditional SIFT algorithm in crop image stitching.A new improved algorithm strategy is proposed from the local and global aspects of the mosaic process. The main research contents are as follows: 1) detecting the SIFT feature points from the input 6 crop images.Each of the two pieces uses BBF algorithm based on k-d tree to match the feature points to establish the matching relationship between the crop images to be stitched. Then, the correct matching feature points are selected by using the RANSAC algorithm, and the transformation matrix between each group of images to be stitched is calculated.Finally, the results of the first two groups are spliced with the last group, and the final 6 crop images are stitched.Through programming and experimental testing, a fast feature point matching method is proposed for crop images, which has obvious pixel contrast among the main scenes.By raising the threshold of pixel contrast, the method can extract the features of the main scene in the image, and reduce the extraction of the useless feature points in the image.Experimental results show that the matching accuracy of the proposed method is about 10% higher than that of the traditional SIFT algorithm in crop image processing.And the speed is twice as high. 2) aiming at the two problems of crop image stitching using traditional SIFT algorithm, the feature points of the non-repeated region of the image to be stitched do not participate in the calculation of the final image mosaic.And for high-resolution crop images, it adds a lot of unnecessary calculation and takes up a lot of memory, resulting in a serious waste of time.It is easy to form the wrong matching point pairs in the feature point matching stage, which increases the computing time of the final transformation matrix.In this paper, a strategy of high resolution crop image stitching is proposed. This strategy firstly reduces the resolution of the image, finds out the approximate overlapping area between the two images to be stitched, and then refines the overlapped area step by step.In order to avoid the above two problems to a certain extent, it can not only improve the speed of high resolution crop image mosaic, but also improve the accuracy of image registration.Experiments show that compared with the traditional SIFT algorithm, the proposed algorithm can improve the matching accuracy by about 20%.
【學(xué)位授予單位】：西北農(nóng)林科技大學(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 鄒承明;侯小碧;馬靜;;基于幾何學(xué)圖像配準(zhǔn)的SIFT圖像拼接算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年04期

2 馬強(qiáng);項(xiàng)昭保;黃良學(xué);王博化;;基于改進(jìn)SIFT和RANSAC圖像拼接算法研究[J];計(jì)算機(jī)技術(shù)與發(fā)展;2016年04期

3 張勇;王志鋒;馬文;;基于改進(jìn)SIFT特征點(diǎn)匹配的圖像拼接算法研究[J];微電子學(xué)與計(jì)算機(jī);2016年03期

4 林克全;勞衛(wèi)倫;;基于sift、對(duì)極幾何和ransac配準(zhǔn)的圖像拼接方法[J];電子測試;2016年01期

5 杜瑞濤;岑峰;;移動(dòng)平臺(tái)上圖像拼接軟件中的視差問題[J];中國科技信息;2015年22期

6 江鐵;朱桂斌;孫奧;;全景圖像拼接技術(shù)研究現(xiàn)狀綜述[J];重慶工商大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年12期

7 馮宇平;戴明;孫立悅;張威;;圖像自動(dòng)拼接融合的優(yōu)化設(shè)計(jì)[J];光學(xué)精密工程;2010年02期

8 馮宇平;戴明;;一種基于角點(diǎn)特征的圖像拼接融合算法[J];微電子學(xué)與計(jì)算機(jī);2009年07期

9 蘭海濱;王平;龍騰;;圖像拼接中相機(jī)鏡頭非線性畸變的校正[J];光學(xué)精密工程;2009年05期

10 劉美瑩;汶德勝;曹紅杏;;基于角點(diǎn)特征的圖像自動(dòng)拼接算法[J];電子器件;2009年02期

相關(guān)博士學(xué)位論文 前6條

1 邵向鑫;數(shù)字圖像拼接核心算法研究[D];吉林大學(xué);2010年

2 馮宇平;圖像快速配準(zhǔn)與自動(dòng)拼接技術(shù)研究[D];中國科學(xué)院研究生院（長春光學(xué)精密機(jī)械與物理研究所）;2010年

3 楊占龍;基于特征點(diǎn)的圖像配準(zhǔn)與拼接技術(shù)研究[D];西安電子科技大學(xué);2008年

4 孫少燕;基于像素灰度的醫(yī)學(xué)圖像剛性配準(zhǔn)方法研究[D];大連理工大學(xué);2007年

5 方賢勇;圖像拼接技術(shù)研究[D];浙江大學(xué);2005年

6 李忠新;圖像鑲嵌理論及若干算法研究[D];南京理工大學(xué);2004年

相關(guān)碩士學(xué)位論文 前1條

1 侯舒維;圖像拼接技術(shù)研究[D];西安電子科技大學(xué);2005年

，

本文編號(hào)：1772828