Adaptive threshold based SIFT image registration algorithm
Hao Qiu, Shuaishuai Peng · 2022
The adaptive threshold based SIFT image registration algorithm (AT-SIFT) is proposed to improve the traditional SIFT algorithm which has the problems of large calculation amount, single matching constraint, and low registration accuracy. Feature points are detected and described by combining FAST operators with and SIFT descriptors. The FLANN algorithm based on adaptive threshold and the improved RANSAC algorithm are used to remove the mis-matching points and solve the transformational matrix. The experimental results show that the algorithm not only improves the matching speed and accuracy but also has relatively strong robustness.