基于角点特征的图像自动拼接算法  

Based on Corner Feature Automatic Image Mosaic Algorithm

作　　者：刘美莹[1,2] 汶德胜[1,2] 曹红杏[1,2] 

机构地区：[1]中国科学院西安光学精密机械研究所,西安710119 [2]中国科学院研究生院,北京100039

出　　处：《电子器件》2009年第2期254-257,共4页Chinese Journal of Electron Devices

摘　　要：提出了一种基于角点特征的图像自动拼接方法。分析了Harris角点检测算子的实现原理及其不足,提出一种改进的Harris角点检测算法提取图像特征角点,减少了计算量,同时提高角点的定位精度,增强了算法的抗噪性能。然后用快速RANSAC算法求出图像变换矩阵H的初值并使用LM非线性迭代算法精炼H,最后采用像素值加权的方法进行图像融合。实验结果表明,该算法能有效提高配准精确性,具有较高的实用价值。An automatic image mosaic algorithm based on corner feature is proposed. First we analyze the principle and disadvantage of the Harris corner detection, based on this, an improved Harris corner detection algorithm is proposed to extract feature points, which reduced the amount of calculation, and improved the positioning accuracy, enhanced the capability of anti-noise. The transforming matrix H is computed with PERANSAC algorithm. LM algorithm is used to purify the transforming matrix M. Finally, image mosaic is completed with smoothing algorithm. The result shows that the accuracy of registration is improved greatly with this algorithm. It is high valuable in practice.

关 键 词：图像拼接 HARRIS角点检测 快速RANSAC 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]