LAUSR

Image registration based on phase correlation has drawn extensive attention due to its high accuracy and efficiency. However, due to changes in image content, nonlinear gray difference, and other noises of image pairs, the line fitting of phase angle points acquired by the singular value decomposition (SVD) and 1-D phase unwrapping is also an intractable problem in the process of phase correlation image registration. In this letter, we propose a probability-guided random sample consensus (RANSAC), namely utilizing a probability to guide the hypothesis search of RANSAC to fit the line accurately and efficiently. The probability of each phase angle point is predicted by a deep convolution neural network (DCNN) of ProbNet we build and the parameters of the network are optimized effectively by integrating probability-guided RANSAC into an end-to-end trainable displacement estimation pipeline. The qualitative experiment is carried out to illustrate the effectiveness of the proposed method. In the quantitative experiments, two competitive methods of locally optimized RANSAC (LO-RANSAC) and least -square fitting (LSQ) and the naive RANSAC method are brought in to compare. The experimental result illustrates that the proposed method has an increase in the success rate of displacement estimation and efficiency.