Image Matching Algorithm Based on OFAST and BRISK Feature Coupling Triple Filtering Strategy
In order to improve the detection speed of image matching algorithm without sacrificing performance,a com-bined OFAST and BRISK coupled triple filtering strategy for image feature point matching algorithm is proposed in this pa-per.Firstly,the OFAST algorithm is used to detect the feature points,and then the BRISK feature description algorithm is used to calculate the descriptors.After that,the Hamming distance is calculated by the violent matching method,and the matching point pairs are pre-screened by the minimum distance filtering method.Before using the PROSAC algorithm,the cosine similarity of the vector is used to eliminate the mismatched feature points,optimize the matching results,and realize the accurate matching of the image.
万方数据
维普
