A Real-Time Matching Algorithm Using Sparse Matrix

Aiming at the shortcomings of the traditional image feature matching algorithm, which is computationally expensive and time-consuming, this paper presents a real-time feature matching algorithm. Firstly, the algorithm constructs sparse matrices by Laplace operator and the Laplace weighted is carried out. Then, the feature points are detected by the FAST feature point detection algorithm. The SURF algorithm is used to assign the direction and descriptor to the feature for rotation invariance, and then the Gaussian pyramid is used to make it scalable invariant. Secondly, the match pair is extracted by the violent matching method, and the matching pair is purified by Hamming distance and symmetry method. Finally, the RANSAC algorithm is used to get the optimal matrix, and the affine invariance check is used to match the result. The algorithm is compared with the classical feature point matching algorithm, which proves that the method has high real-time performance under the premise of guaranteeing the matching precision.