非线性尺度和改进ORB的配准方法

ORB algorithm doesn`t perform well in scale invariance and SIFT algorithm with high time complexity does not respect the natural boundaries of images. Aiming at the issue, we put forward an image registration algorithm based on the nonlinear scale space and improved the ORB. Firstly, the nonlinear scale space is used to smooth noise and retain object boundaries, to set scale parameters based on image entropy and to set proper distance between feature points, so that the ORB detectors are stable. Then, maxima is searched for in scale and spatial location and descriptors are computed. At last, we match features with RANSAC algorithm and hamming distance. We testify our improved algorithm through experiments and demonstrate that it can shorten time of registration, improve greatly robustness and perform well.