Image gradient comparison-based image fusion method, storage medium and terminal equipment

Abstract

The invention belongs to an image fusion method. In order to solve the technical problems that a threshold comparison method commonly adopted for fusion of high-gain and low-gain images at present is large in workload before use, calibration must be carried out again if threshold drift is caused by changes of an external environment in the use process and the fusion effect is not good due to the fact that ripples are likely to occur in a transition zone of a saturated region and an unsaturated region during normal fusion, the invention provides an image fusion method based on image entropy comparison, a computer readable storage medium and terminal equipment. According to the fusion method, the rule that a measured value is smaller than an actual value when pixels of a high-gain image are saturated is utilized, and large-dynamic-range image fusion is achieved by comparing the sum of gradients of the pixels of the high-gain image and the low-gain image in the horizontal direction and the vertical direction. The computer readable storage medium and the terminal equipment execute the fusion method.

Description

technical field [0001] The invention belongs to an image fusion method, in particular to an image fusion method based on image gradient comparison, a computer-readable storage medium and a terminal device. Background technique [0002] Image diagnosis is widely used in physical and biological research, and it is an important means to discover new phenomena and study new mechanisms. Especially in research fields such as detonation effect, plasma experiment, bioimaging and biomedicine, the target image of the diagnostic test often has a large dynamic range, thus requiring the imaging system to also have a large dynamic range. [0003] At present, it is a widely used imaging technology to obtain two high-gain and low-gain images by using a dual-gain image sensor or multiple exposure technology, and then fuse them to obtain a large dynamic range image. Among them, the fusion effect of high-gain and low-gain images is very important to obtain high-quality images with large dynam...

AI Technical Summary

Problems solved by technology

[0005] The present invention solves the threshold comparison method widely used in the fusion of two images with high and low gain at present. The workload before use is large. If the threshold value drifts due to changes in the external environment during use, it must be re-calibrated, and during normal fusion, the saturation area Ripples are prone to appear in the transition zone of the unsaturated region and the technical problem of poor fusion effect. An image fusion method based on image gradient comparison, a computer-readable storage medium, and a terminal device are provided.

Images