计算机技术与发展2024，Vol.34Issue(1)：59-64,6.DOI:10.3969/j.issn.1673-629X.2024.01.009
基于改进SURF的增强现实图像匹配方法
Augmented Reality Image Matching Method Based on Improved SURF
摘要
Abstract
Aiming at the problems of poor robustness and efficiency of traditional augmented reality image matching algorithms,an improved SURF matching algorithm is proposed.Firstly,the SURF algorithm is used to detect the feature points,then the Haar wavelet template is used to determine the main direction of the feature,and then the feature descriptor is constructed after the main direction of the feature is obtained.Because the traditional SURF algorithm uses rectangular descriptors up to 64 dimensions,which is computationally in-tensive and robust.Therefore,the DAISY circle descriptor is used instead of the rectangle descriptor in the original algorithm.DAISY is a three-layer concentric circle structure,each layer contains 8 sampling points,which can obtain 25 dimensional descriptors.This structure greatly enhances the robustness of the algorithm and reduces the computational complexity.Then Euclidean distance is computed using the feature descriptor for feature point matching.Finally,the resulting set of matching points is optimized using random sampling consistency(RANSAC)and triangular irregular network(TIN)to eliminate mismatched points.The experimental results show that the time complexity of the proposed algorithm is slightly increased,the robustness becomes stronger,and the efficiency and matching accuracy of the proposed algorithm are also greatly improved,with the average accuracy reaching more than 95%.关键词
增强现实/图像匹配/SURF算法/DAISY描述符/随机抽样一致/三角不规则网络Key words
augmented reality/image matching/SURF/DAISY descriptor/random sample consensus/triangular irregular network分类
计算机与自动化引用本文复制引用
贾一鑫,邓魏永,殷强,毋涛..基于改进SURF的增强现实图像匹配方法[J].计算机技术与发展,2024,34(1):59-64,6.基金项目
国家自然科学基金(61806160) （61806160）
