Infrared and Visible Image Fusion Algorithm Based on Target Extraction

Abstract

With the purpose to highlight infrared targets and improve the fusion quality of infrared and visible images, an infrared and visible image fusion algorithm based on target extraction is proposed. Firstly, impose Canny edge extraction and Otsu threshold segmentation on the infrared images, fuse the binary images extracted from them and obtain the infrared target images. Secondly, lift wavelet transform on V components of the infrared target images, infrared images and the visible images after HSV color space transform, adopt the fusion rules based on regional energy, mutual information and matching degree for high-frequency coefficients and the fusion rules based on regions for low-frequency coefficients under the guidance of low-frequency coefficients of infrared target images for the fusion of low-frequency coefficients. The contrast experiment of image fusion algorithm shows that the fusion algorithm in this paper can better highlight infrared target information, provide rich background details, and is superior to the traditional algorithm in image clarity and human visual effect.