Fusion Detection Method of Infrared Image and Visible Light Image Based on Visual Attention Model

Abstract

The invention provides a fusion detection method of infrared images and visible light images based on a visual attention model. The method includes: preprocessing the collected infrared images and visible light images respectively; extracting objects of interest from the preprocessed infrared images and visible light images based on the visual attention model of the human eye; using the preprocessed visible light images as Background, the corresponding preprocessed infrared image and the visible light image as the background are grayscale image fused to obtain a grayscale fused image; the grayscale fused image is subjected to pseudo-color mapping annotation of the target of interest, and the target pseudo-color image is obtained and output. Color fused image. The application of the present invention can solve the problem in the prior art that the target of interest is weakened in the fused image, greatly improve the accuracy and reliability of the detection and identification of the target of interest, and reduce the difficulty of target recognition.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a fusion detection method of infrared images and visible light images based on a visual attention model, which can be applied to the detection and recognition of faint targets or targets with complex backgrounds in fusion images. Background technique [0002] The infrared thermal imaging system mainly relies on the radiation of the target and the background to generate the scene image, but the contrast of the infrared image is poor, and it is only sensitive to the radiation of the target scene, and is not sensitive to the brightness change of the scene. Compared with infrared images, visible light images can provide more target details, which is beneficial to human observation. Therefore, using infrared and visible light image fusion technology, it is possible to fully reflect the information redundancy and complementarity among multi-source images obtained by ...

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a fusion detection method of an infrared image and a visible light image based on a visual attention model, which can solve the problem in the prior art that the target of interest is weakened in the fusion image, and greatly improve the detection of interest. The accuracy and reliability of target detection and recognition reduce the difficulty of target recognition

Images