Infrared and visible light image registration method and system and storage medium

Abstract

The invention discloses an infrared and visible light image registration method and system and a storage medium. The method comprises the following steps: preprocessing an infrared image and a visible light image; performing significance enhancement on the infrared image and the visible light image through frequency tuning to obtain a significance response diagram; phase consistency detection being carried out on the obtained significance response diagrams of the infrared light and the visible light, and similarity structure edge features in the two images being extracted; and feature point extraction being performed on the processed similarity structure edge images, the extracted feature points being matched by using a matching algorithm, mismatching points being screened, and a registration image being obtained through calculation. According to the method, the features of the image structure information are adopted for registration, the problem that effective features are difficult to extract from infrared and visible light different-source images with large differences in a traditional method is solved, and the method has the advantages of improving the image registration precision and speed, can be applied to an embedded platform and has wide market prospects and application value.

Description

technical field [0001] The invention belongs to the field of image registration technology and computer vision, and in particular relates to a method, system and storage medium for infrared and visible light image registration. Background technique [0002] Infrared and visible light image registration is the research focus and difficulty of heterogeneous image registration. The infrared image reflects the temperature radiation information of the object, and the visible light image reflects the light reflection information of the object. The two information complement each other and can realize the registration and fusion of heterogeneous images. It has a wide range of applications in military investigation, target tracking, pattern recognition and other fields. . The image registration method based on feature points is widely used in the field of image registration because of its high calculation speed and good robustness. It first needs to extract some feature elements (...

AI Technical Summary

Problems solved by technology

However, due to differences in imaging principles and shooting conditions, there are large differences between infrared and visible light images, large noise interference, and low grayscale contrast and signal-to-noise ratio of infrared images. The feature points detected by the feature point extraction operator The number is much smaller than that of visible light images, which cannot meet the actual image registration requirements

Images