A method and device for image fusion

Abstract

An embodiment of the invention discloses an image fusion method and a device thereof. The method comprises the steps of calculating an overlapping area of video frames in two video paths; by means of a frame difference method, calculating all motion areas which correspond with the overlapping area, and calculating the motion amounts of the motion areas; according to the overlapping area and the motion areas, determining a starting point of each suture line; through calculating a gray scale difference matrix of the overlapping area, and according to the starting point and the motion amount, selecting a target point which accords with a preset rule; and according to the starting point and the target point, determining the suture line which corresponds with each starting point. Some suture lines which accord with a preset condition are selected from the suture lines as target suture lines. Video frame fusion can be realized according to the target suture lines. Obviously, the motion areas in the video frames are effectively avoided in determining the target suture lines so that overlapping, offsetting and ghost can be effectively prevented in picture splicing in the image which is fused according to the suture lines.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image fusion method and device. Background technique [0002] As a branch of information fusion, image fusion is a hotspot in current information fusion research. The data form of image fusion is an image containing light and shade, color, temperature, distance and other scene characteristics. The images can be given as one, or as a column. Image fusion is the fusion of two or more image information into one image, so that the fused image contains more information and can be more convenient for human observation or computer processing. The goal of image fusion is to reduce the uncertainty and redundancy of the output on the basis of maximizing the combination of relevant information under the actual application goal. The advantages of image fusion are obvious. It can expand the time and space information contained in the image, reduce uncertainty, increase ...

AI Technical Summary

Problems solved by technology

[0004] In the traditional way, the image fusion is directly performed according to the projection transformation matrix obtained by registration, which often leads to obvious stitching seams in the final fused image

Images