Infrared and visible image registration based on hypercolumns

Abstract

Image registration is a challenging and critical task in computer vision and image processing. As the typical multi-modal image, infrared and visible image have greatly difference in gray scale, which makes the registration method based on hand-crafted features have a low accuracy. In this paper, we introduce a method based on hypercolumns and matching strategy. Combining different layers features in Convolutional Neural Network using hypercolumns, we can get more comprehensive and essential features to achieve a higher accuracy. Meanwhile we use coordinate difference acquired by automatic selection as the spatial distance constraint. Firstly, the key points are extracted by corner detection from the infrared and visible images. Then the features of the key points are extracted using the hypercolumns. Finally, similarity metric is performed by spatial geometric constraints. The experimental results show that the accuracy of our method is higher than that of the traditional method.