基于尺度不变特征变换的图像快速拼接算法  

A Fast Automatic Image Stitching Algorithm Based on Scale Invariant Feature Transform

作　　者：李铁军[1] 陈哲[1] 王任享[2] 

机构地区：[1]北京航空航天大学自动化学院,北京100083 [2]西安测绘研究所,西安710054

出　　处：《微计算机信息》2008年第12期282-283,259,共3页Control & Automation

基　　金：航空基础科学基金(20060818003)

摘　　要：针对基于灰度级相似的图像拼接算法的缺点,提出一种基于尺度不变特征变换(Scale Invariant Feature Transform)的快速图像拼接算法。该算法利用图像特征在尺度空间具有平移、旋转和仿射不变性,快速提取图像的关键特征点,建立图像的匹配关系。实验证明,该算法在地物特征较少或较复杂的区域,都能实现自动拼接,且具有较强的适应能力、防抖能力和抗噪声能力。In order to overcome the available disadvantages of the intensity-based image stitching,a fast automatic image stitching al-gorithm based on Scale Invariant Feature Transform (SIFT) was proposed. The key feature points of image were extracted,the point transformation parameters between two images by using invariability of image in this algorithm,which are the translation,rotation and affine of image in the scale space. This algorithm was applied to image stitching,simulation result proved that the proposed ...

关 键 词：图像拼接 关键特征点 SIFT 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]