基于双边滤波和AGAST-BEBLID的图像匹配算法

Image Matching Algorithm Based on Bilateral Filtering and AGAST-BEBLID

摘要:

针对传统AGAST特征匹配算法存在精度差、鲁棒性低等问题,提出一种基于双边滤波和AGAST-BEBLID的图像匹配算法。首先使用双边滤波进行去噪和增强图像边缘细节效果。其次使用BEBLID算法在特征提取阶段创建高效二进制描述子,来产生更好的局部特征描述。然后使用GMS算法结合汉明距离来筛选KNN匹配后的图像,达到特征粗匹配。最后使用GC-RANSAC算法在误匹配剔除阶段进行局部最优模型拟合,得到图像特征精匹配。实验结果显示:改进后的算法在复杂环境下的总体平均准确率较AKAZE,BRISK和SIFT分别提高了10.57%,17.20%和19.45%。

Abstract:

Aiming at the problems of poor accuracy and low robustness of traditional AGAST feature matching algorithm, an image matching algorithm based on bilateral filtering and AGAST-BEBLID is proposed. Firstly, bilateral filtering was used to de-noise and enhance the image edge detail effect. Secondly, BEBLID algorithm was used to create efficient binary descriptors in the feature extraction stage to generate better local feature descriptions. Then GMS algorithm combined with Hamming distance was used to filter the KNN matched images to achieve coarse feature matching. Finally, GC-RANSAC algorithm was used to fit the local optimal model in the mismatching elimination stage, and the image features were accurately matched. The experimental results show that the overall average accuracy of the improved algorithm in complex environments is 10.57%, 17.20%, and 19.45% higher than AKAZE, BRISK and SIFT respectively.