The principal of SIFT algorithm is discussed. In order to solve the problem of low efficiency caused by the descriptor during the matching process, instead of the 128-dimensions descriptor adopted in the original algorithm , a 64-dimensions descriptor is put forward. Compared with the original one, the new descriptor expanded the statistical range of adjacent feature points, reinforced the feature information and reduced the feature descriptor' s dimensions; the BBF-based K-dimension-tree is used in the feature matching stage in which Euclidean distance is used to measure the similarity. This method improved the matching rate. According to the experiment, results show that the matching time is greatly shortened by 5% ～ 15%. In comparison with the original descriptor, the new descriptor is competitive in effectiveness.%对尺度特征不变SIFT算法进行了研究.针对原算法中128维特征描述子在匹配过程中效率低的情况,提出64维特征描述子.该描述子增加了特征点邻域的统计范围,增强了特征点的特征信息,降低了特征描述子的维数;特征点匹配阶段,采用欧氏距离作为度量,采用基于BBF的Kd-树对特征点进行匹配,提高了匹配速率.实验表明,匹配速率提高了5％到15％,配准精度与原算法相近.
展开▼
