Fast non-rigid image feature matching for agricultural UAV via probabilistic inference with regularization techniques

Image feature matching is one of the most important fundamental technologies for agricultural unmanned aerial vehicle (UAV). There has been some attempt on this task, but the performance and efficiency are still not satisfactory due to the complexity of UAV images, especially undergo non-rigid transformation. In this paper, we propose a probabilistic method to address these problems. We start by creating a set of putative correspondences based on the feature similarity and then focus on removing outliers from the putative set and estimating the transformation as well. This is formulated as a maximum likelihood estimation of a Bayesian model with latent variables indicating whether matches in the putative set are inliers or outliers. We enforce three effective regularization techniques on the correspondence in a reproducing kernel Hilbert space simultaneously, which helps to find an optimal solution. The problem is finally solved by using the expectation-maximization algorithm, and the closed-form solution of the transformation is derived in the maximization step. Moreover, a fast implementation based on sparse approximation is given which reduces the method computation complexity to quadratic without performance sacrifice. Extensive experiments on real farmland images demonstrate accurate and robust results of the proposed method which outperforms current state-of-the-art methods, particularly in case of severe outliers.