一种基于金字塔相似层的SIFT双向匹配算法研究  

Research on Sift Bidirectional Matching Algorithm Between the Similar Prymid Layers

作　　者：文雪中 马红[1] 

机构地区：[1]重庆市勘测院,重庆400020

出　　处：《城市勘测》2015年第4期99-102,共4页Urban Geotechnical Investigation & Surveying

基　　金："十二五国家科技支撑计划"课题(2011BAH12B07-03)

摘　　要：针对SIFT特征匹配算法误匹配点多和特征空间中遍历搜索速度慢的问题,提出了一种基于分层策略的SIFT双向特征匹配算法。首先,建立待匹配图像的金字塔影像,计算图像的SIFT特征点,并根据不同金字塔层将特征点划分为不同的集合;其次,选择某一层集合,在另一图像中寻找相似层,并确定两幅图像金字塔层之间的相似关系,在相似层之间设置阈值完成单方向匹配;然后,利用单向匹配结果完成已配对点集合的反向匹配。实验结果证明本文方法能降低匹配时间,提高匹配正确率。Aimed at the high wrong match points and slow matching speed in searching the whole database of feature points of SIFT feature matching method,we proposed an improved matching method of searching between the similar pyramid layers using bidirectional matching. First,we calculate the pyramid image and SIFT feature points of the input images,and divid the feature points into different sets according to the different pyramid layers. Then a layer set in the input image pyramid is chosen to search for the similar layer in the another image pyramids,and then the similarity between tow image pyramid layers is determined,and matching the feature points between the similarity pyramid layers by single direction. Finally,matches the feature points which have been matched by reverse direction. The experimental results demonstrate that this approach can reduce the matching time and improve the matching accuracy.

关 键 词：SIFT特征匹配 金字塔 双向匹配 图像配准 

分 类 号：P234.1[天文地球—摄影测量与遥感]