Different-source image fusion method based on salient target region extraction and NSST (Non-subsampled Shearlet Transform)

Abstract

The invention discloses a different-source image fusion method based on salient target region extraction and NSST (Non-subsampled Shearlet Transform). The method comprises the following steps that: firstly, extracting the salient target region of an infrared image; carrying out registration on infrared and visible images to obtain an affine transform matrix; through the affine transform matrix, obtaining the position of the salient target region of the infrared image in the visible light image; carrying out NSST on the infrared and visible light image; utilizing different methods to carry outfusion on the NSST results of a target area and a non-target area of two images; and finally, through NSST inverse transform, obtaining a final fusion result. By use of the method, two different-source images of the infrared light and the visible light can be effectively fused, a fusion result can better highlight and keep the target, and the background detail information of the non-target area inthe visible light image can be more favorably kept.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a heterogeneous image fusion method based on salient target region extraction and NSST. Background technique [0002] With the development of sensor technology, image sensors of different bands have been widely used, and the heterogeneous image fusion technology developed with it has also received more and more attention. Heterogeneous image fusion can fuse images collected by different image sensors in the same scene to obtain a fusion image with richer information. It has important applications in remote sensing detection, military reconnaissance, security monitoring, medical health, industrial production and other fields. [0003] Infrared images can highlight the characteristics of infrared thermal target areas, but often the images lack detailed information and image contrast is reduced; while visible light images can reflect the texture and details of the imaging ar...

AI Technical Summary

Problems solved by technology

The most direct fusion idea is the direct averaging method, but the edges and details of the image are easy to be smoothed, and the fusion effect is limited

At present, there is a mainstream infrared and visible light fusion algorithm based on the transform domain method, such as wavelet transform, pyramid transform, Curvelet transform and Contourlet transform, etc., but these methods do not have translation invariance, which can easily lead to blurred image edge details.

Based on the non-subsampling Contourlet transform, although it has translation invariance and good fusion effect, the algorithm complexity is high

A common problem in the field of infrared and visible light image fusion is that when the light is dim and the gray scale of the background and the target are similar, the fusion image is prone to problems such as insufficient background detail information and insufficiently accurate and prominent targets.

In addition, due to the low signal-to-noise ratio of infrared images, the interference of noise will affect the quality of image fusion

Images