摘要
为了减少图像拼接方法的计算复杂度,提出一种基于尺度不变特征变换(SIFT)特征矢量图的快速图像拼接方法.该方法首先结合相位相关算法,确定待拼接图像的重叠区域,限定SIFT特征点检测范围;然后考虑特征点的空间位置信息,构建SIFT特征矢量图像,以便在特征匹配时限制匹配点的搜索范围,快速获得匹配点对.实验结果表明,该方法减少了大量的不必要搜索,提高了图像拼接速度.
In order to reduce the computational complexity of image stitching method, we proposed a fast image stitching method based on scale invariant feature transform （SIFT） feature vector image. Firstly, the method combined the phase correlation algorithm to determine the overlapping regions of the images to be stitched, and the detection range of the SIFT feature points was defined. Then we considered the spatial location information of feature points, constructed the SIFT feature vector images in order to limit the searching ranges in the feature matching, and got the matching points quickly. Experimental results show that the new method reduces a lot of unnecessary search, and improves the speed of image stitching.
作者
陈月
赵岩
王世刚
CHEN Yue ZHAO Yan WANG Shigang(College of Communication Engineering, J ilin University, Changchun 130012, China)
出处
《吉林大学学报（理学版）》
CAS
CSCD
北大核心
2017年第1期116-122,共7页
Journal of Jilin University:Science Edition
基金
国家自然科学基金(批准号:61271315)
关键词
图像拼接
尺度不变特征变换
特征矢量图
特征匹配
image stitching
scale invariant feature transform （SIFT）
feature vector image
feature matching
