Image fusion method and device based on NSST and adaptive dual-channel PCNN

Abstract

The invention provides an image fusion method and a device based on NSST and adaptive dual-channel PCNN. NSST is used as a multi-scale transform tool to decompose the image, NSST removes the sample operation in the decomposition phase, and has translation invariance, at the same time, a localize small size shearing filter can avoid spectral aliasing, so that the effect of image decomposition and reconstruction is better, using an adaptive simplified two-channel PCNN model with three kinds of link strengths, through three different link strengths, the features of the image are integrated, the infrared and visible images are fused effectively, the contrast is high, the texture information and detail information are well preserved, and the image transition is natural, no artifact phenomenon occurs.

Description

technical field [0001] The invention relates to the field of image fusion, in particular to an image fusion method and device based on NSST and adaptive dual-channel PCNN. Background technique [0002] The concept of image fusion (Multi-source Image Fusion) was proposed in the early 1970s. It mainly studies the internal relationship between images. By using appropriate algorithms, two or more images with redundant Multi-source images with redundant, diverse and complementary information are fused, and the generated fused image contains richer information. The fusion of infrared and visible light is currently the most widely used. The effective combination of the two can combine the respective advantages of the two images to form a fusion image with high contrast, enhanced background, and prominent targets, which is more conducive to quickly and accurately detecting and discovering hidden and camouflaged objects. Target. [0003] In recent years, scholars have proposed many...

AI Technical Summary

Problems solved by technology

The document "A fusion algorithm for infrared and visible images based on adaptive dual-channel unit-linking PCNN in NSCT domain [J], Infrared Physics & Technology, 2015, 69: 53–61" proposes an adaptive dual-channel PCNN model to solve the above The problem is that although a certain effect has been achieved, there are phenomena such as black artifacts and target halos.

The main factor is that the spectrum of the infrared and visible light images is quite different, which leads to a decrease in the stability of the link strength value in the PCNN model, and the link strength reflects the intensity of the human visual system's response to different feature regions in the image, which eventually leads to the fusion of images. Defects such as discontinuities and blurred edges

Images