A Fusion Method of Infrared and Visible Light Images Based on Interactive Nonlocal Mean Filtering

Abstract

The invention relates to an infrared light image and visible light image fusion method based on interactive non-local average filtering. The method mainly aims to solve the problems that a fused image obtained through an existing infrared light image and visible light image fusion method is low in definition, contrast and spatial resolution. The method comprises the implementation steps of (1) carrying out interactive non-local average filtering on an input infrared light image and an input visible light image to obtain base layer images; (2) subtracting the corresponding base layer image from the infrared light image to obtain a detail image of the infrared light image, and subtracting the corresponding base layer image from the visible light image to obtain a detail image of the visible light image; (3) calculating the neighboring window statistical characteristics of the detail images to obtain a fusion weight plot of the infrared light image and a fusion weight plot of the visible light image; (4) enabling the fusion weight plot of the infrared light image and the fusion weight plot of the visible light image to act on the infrared light image and the visible light image respectively, and carrying out weight fusion on the infrared light image and the visible light image which have undergone action of the corresponding fusion weight plots to obtain a fused image. By means of the infrared light image and visible light image fusion method based on interactive non-local average filtering, the fused image high in definition, contrast and spatial resolution can be obtained, and the fusion effect is good. The infrared light image and visible light image fusion method based on interactive non-local average filtering can be used in the fields of human vision, machine cognition and the like.

Description

technical field [0001] The invention belongs to the technical field of image fusion processing, and in particular relates to an infrared and visible light image fusion method based on interactive non-local mean filtering. Background technique [0002] Image fusion is a technology that organically integrates image information of the same scene obtained by two or more sensors. Fused images are more conducive to human and machine visual perception and other image processing tasks, such as: image enhancement, face recognition, feature extraction and object detection etc. Because image fusion technology can enrich the information and visual effects of images, image fusion is widely used in computer vision, medical imaging, remote sensing measurement and other fields. [0003] Since the 1980s, multi-sensor image fusion has aroused widespread interest and research upsurge, and it has broad application prospects in machine learning, remote sensing, computer vision, medical image pr...

AI Technical Summary

Problems solved by technology

However, NSCT also has its own shortcomings: since the direction filter used by NSCT is a non-subsampling filter bank of fan-shaped filter, the band-pass direction sub-band coefficients are obtained through this filter; thus, the calculation amount of the image fusion method based on NSCT is relatively large. large, which is not conducive to practical applications; and the clarity and spatial resolution of the fusion image are still relatively low, and the overall effect is still not satisfactory

Images