Heterogeneous scene matching algorithm based on gradient direction distribution field

Abstract Heterogenous scene matching is one of the key technologies in the field of computer vision. The image rotation problem has been a hot and difficult problem in the field of heterogenous scene matching. In this paper, a heterogenous scene matching method based on the gradient direction distribution field is proposed. The Distributed field theory is introduced into the heterogenous scene matching for the first time. First, the gradient direction distribution field is constructed and fuzzified, and then the effective regions are selected. Then, the concept of main direction distribution field is defined to solve the matching errors due to the existence of rotational transformations between heterogeneous source images. Third, the Chi-square distance is introduced as a similarity measure. At last, the hill-climbing method search strategy is adopted, which greatly improves the efficiency of the algorithm. Experimental results on 8 pairs of infrared and visible heterogenous images demonstrate that the proposed method outperforms the other state-of-the-art region-based matching methods in terms of robustness, accuracy and real-time performance.