Infrared image and visible image registration method based on visual attention

Abstract

The invention discloses an infrared image and visible image registration method based on a visual attention mechanism. The infrared image and visible image registration method based on the visual attention mechanism comprises the following steps of inputting an original infrared image and an original visible image, and obtaining a visual salience region of the infrared image and a visual salience region of the visible image through a visual attention mechanism model; carrying out rough matching on the visual salience region of the infrared image and the visual salience region of the visible image through invariant moment calculation of the Hu moment; searching for the center of mass in the visual salience region of the infrared image and the center of mass in the visual salience region of the visible image after rough matching is accomplished, using the centers of mass as visual salience points, and using the visual salience points to represent the visual salience regions; carrying out fine matching on the visual salience points on the basis of the de-mean normalization cross-correlation principle; purifying accurately-matched images through an RANSAC algorithm, calculating a registration estimation function, carrying out image transformation through the registration estimation function to achieve registration and output of the images. According to the infrared image and visible image registration method based on the visual attention mechanism, due to the fact that the visual attention mechanism of human eyes is simulated, serves as an image characteristic detection method, and is used for extracting stable characteristics, after matching is carried out, registration between the infrared image and the visible image is accurately achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a registration method of infrared images and visible light images based on a visual attention mechanism. By simulating the "region of interest" of the image noticed by the human eye, the information of the "region of interest" is used to perform infrared image registration. Registration with visible light images. Background technique [0002] Image registration technology is the process of spatially aligning images taken in the same area at different angles of view, at different times, with different sensors or under different lighting conditions. The images obtained by shooting the same scene are a series of projections of the real three-dimensional world to the imaging plane at different times. There is a large correlation and information redundancy between images, so no matter what form the processed image takes Changes in the image, or what kind of senso...

AI Technical Summary

Problems solved by technology

However, since the infrared reflects the radiation information of the scene, and the visible light reflects the reflection information of the scene, the imaging conditions and scenes of the two have certain complexity, so the correlation between the infrared and visible light images is small, and the grayscale characteristics of the images are very different. Lack of consistent features, making registration difficult

[0006] In order to solve the registration problem between infrared images and visible light images, many effective algorithms have been produced in various fields according to their own needs. There are many studies on the registration of infrared and visible light images in military and remote sensing. The contents of these images are generally It is based on the entire scene. There may be some obvious landmarks in this type of image that can provide more favorable feature points for matching, such as the corners of tanks, the boundaries of regions, etc.; and infrared and visible light images in industrial and civil fields Sometimes it may be difficult to obtain such feature points, because they often only represent the local area of ​​the object. For the registration of such images, how to stably extract the common features of infrared and visible light images is still an urgent problem to be solved. topic

Images