一种自适应搜索范围的SIFT特征点快速匹配算法

摘要

Aiming at the high time cost of feature vectors matching in SIFT, a new fast algorithm, called Auto ARV&DP, of self⁃adaptive search scope for SIFT matching is put forward. Firstly, an appropriate reference vector is computed based on the feature vectors set. Secondly, a self⁃adaptive search scope is determined by this reference vector. Finally, the matching of SIFT is performed in a small feature vectors set, which is filtered by norm. Experi⁃mental results showed that compared with the classical BBF algorithm, Auto ARV&DP can effectively decrease the time cost of feature vector matching of SIFT with no loss of matching performance when the size of feature vector set is large.%针对SIFT特征向量匹配时间成本高的问题，提出了一种自适应搜索范围的快速匹配算法－AutoARV＆DP。该算法首先根据特征向量集合计算一个合适的参考向量，然后自适应确定一个搜索范围，最后在一个通过距离过滤后的较小搜索空间中进行特征向量匹配。实验结果表明，与经典的BBF算法相比较，AutoARV＆在获得满意匹配效果的同时，能够有效地降低SIFT特征点匹配的时间成本。