江苏科技大学学报(自然科学版)
江囌科技大學學報(自然科學版)
강소과기대학학보(자연과학판)
JOURNAL OF JIANGSU UNIVERSITY OF SCIENCE AND TECHNOLOGY(NATURAL SCIENCE EDITION)
2015年
2期
164-169
,共6页
ORB%空间一致性检测%改进RANSAC%单应矩阵%提纯
ORB%空間一緻性檢測%改進RANSAC%單應矩陣%提純
ORB%공간일치성검측%개진RANSAC%단응구진%제순
ORB%spatial consistency check%improved RANSAC%homography%purification
图像拼接技术能够很好地解决单张拍摄照片的视野狭窄问题,是数字图像处理的一个重要分支。其一般步骤是先粗匹配,后提纯,然而在用随机抽样一致性算法( random sample consensus , RANSAC)提纯时,将粗匹配的所有特征点对都进行迭代运算,运算量较大,导致拼接速度慢。针对该问题,文中采用了ORB( oriented FAST and rotated BRIEF )算法,并结合空间一致性检测理论来改进RANSAC算法,以提高拼接速度。文中采用ORB算法提取特征点,并进行粗匹配;在RANSAC提纯之前,先进行一次空间一致性检测,从而缩小RANSAC抽样总量,减少迭代次数。分别用ORB+改进RANSAC算法和ORB+RANSAC算法对两组图片进行对比实验,实验表明,ORB和改进RANSAC算法的结合在保证匹配精度的基础上提高了匹配速度。
圖像拼接技術能夠很好地解決單張拍攝照片的視野狹窄問題,是數字圖像處理的一箇重要分支。其一般步驟是先粗匹配,後提純,然而在用隨機抽樣一緻性算法( random sample consensus , RANSAC)提純時,將粗匹配的所有特徵點對都進行迭代運算,運算量較大,導緻拼接速度慢。針對該問題,文中採用瞭ORB( oriented FAST and rotated BRIEF )算法,併結閤空間一緻性檢測理論來改進RANSAC算法,以提高拼接速度。文中採用ORB算法提取特徵點,併進行粗匹配;在RANSAC提純之前,先進行一次空間一緻性檢測,從而縮小RANSAC抽樣總量,減少迭代次數。分彆用ORB+改進RANSAC算法和ORB+RANSAC算法對兩組圖片進行對比實驗,實驗錶明,ORB和改進RANSAC算法的結閤在保證匹配精度的基礎上提高瞭匹配速度。
도상병접기술능구흔호지해결단장박섭조편적시야협착문제,시수자도상처리적일개중요분지。기일반보취시선조필배,후제순,연이재용수궤추양일치성산법( random sample consensus , RANSAC)제순시,장조필배적소유특정점대도진행질대운산,운산량교대,도치병접속도만。침대해문제,문중채용료ORB( oriented FAST and rotated BRIEF )산법,병결합공간일치성검측이론래개진RANSAC산법,이제고병접속도。문중채용ORB산법제취특정점,병진행조필배;재RANSAC제순지전,선진행일차공간일치성검측,종이축소RANSAC추양총량,감소질대차수。분별용ORB+개진RANSAC산법화ORB+RANSAC산법대량조도편진행대비실험,실험표명,ORB화개진RANSAC산법적결합재보증필배정도적기출상제고료필배속도。
Image stitching technology can better solve confined vision of a single photograph , which is an impor-tant branch in the field of digital image processing .The general image stitching steps are coarse matching and then purification , however , RANSAC ( random sample consensus ) algorithm has large amount of computation , lower efficiency problem when going on point-purification .This paper uses ORB ( oriented FAST and rotated BRIEF) algorithm and spatial consistency check theory for improving RANSAC algorithm in order to improve stitching speed .This paper uses ORB algorithm to extract feature points and carry out coarse matching .Before RANSAC purifying , this paper uses spatial consistency check theory to reduce the amount of RANSAC sampling and decrease the number of iterations .With two pairs of images ,this paper adopts ORB +improved RANSAC and ORB+RANSAC algorithm to have a purification experience .Experiments show that ORB combined with im-proved RANSAC algorithm can increase the matching speed and guarantee matching accuracy .