一种高鲁棒性的全景图拼接算法  

A Highly Robust Stitching Algorithm of Panorama

作　　者：夏倩[1] 陈孝威[1] 

机构地区：[1]贵州大学计算机科学与技术学院,贵州贵阳550025

出　　处：《计算机工程与科学》2008年第2期51-54,共4页Computer Engineering & Science

基　　金：国家教育部春晖计划基金资助项目(Z2004-1-520)

摘　　要：为了提高全景图生成的效率和准确度,本文提出了一种高鲁棒性的全景图像拼接算法。首先根据初始图像构造图像金字塔,然后结合最小局部熵差和自适应阈值的序贯相似检测算法实现全景图的拼接。实验结果表明,该算法具有抗噪声和几何失真的能力,对一般条件下获取的图像表现出较好的鲁棒性。A highly robust stitching algorithm of panorama is proposed to improve the efficiency and accuracy of building panorama. Firstly, a pyramid-based image is formed accoding to the input images, and then the least local entropy and a sequential similarity detection alogrithm with an adaptive threshold are used to complete the stitching of the panoramic images. The experiments show that the method has the properties of anti-noise and anti-geometrical deformation. And it indicates a high robustness to the images taken by a camera in common conditions.

关 键 词：虚拟现实 局部熵差 序贯相似性检测 全景图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]