一种图像自动拼接的快速算法  

A Fast Automatic Image Stitching Algorithm

作　　者：侯舒维[1] 郭宝龙[1] 

机构地区：[1]西安电子科技大学机电工程学院,西安710071

出　　处：《计算机工程》2005年第15期70-72,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(69975015);教育部优秀青年教师资助计划项目

摘　　要：针对现有基于灰度级相似的图像拼接方法的缺点,提出了一种图像自动拼接的快速算法。该算法综合考虑了图像拼接的精度和速度,在基准特征块的提取上,采用简单的边缘信息阈值法,实现了基准块的自主选取,提高了图像拼接的精度;在块搜索上,采用金字塔式分层搜索策略,提高了图像拼接的速度。实验证明,该算法扩展了传统拼接算法的适用范围,具有较好的性能。By analyzing the available disadvantages of the intensity-based image stitching, a fast automatic image stitching algorithm is proposed.This algorithm takes into account the precision of image stitching as well as the speed of it, as to the pick-up of the base feature block, a simple method of edge information threshold is used, which realizes the automatic pick-up of base feature block, therefore improves the precision of image stitching. In the problem of searching matching block, a hierarchical search strategy is employed, which improves the speed of image stitching. The experiments show that the proposed algorithm greatly extends the scope of traditional image stitching algorithm and has good capabilities.

关 键 词：图像拼接 配准 特征块 图像融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]