An Intelligent Infrared Image Scene Enhancement Method

Abstract

The present invention proposes an intelligent infrared image scene enhancement method, comprising: using an improved joint bilateral filter to jointly calculate two adjacent frames of infrared images to obtain the detail layer component and the base frequency layer component of the reference frame image; Utilize the kernel function of the guided gray level similarity item to control the enhancement range of the detail layer component and eliminate the edge gradient flip effect, and use the improved histogram calculation method to control the gray level redistribution of the entire image in the base frequency layer component; The processed detail layer image and the base frequency layer image are superimposed and restored to enhance the scene of the original reference frame infrared image. The present invention effectively overcomes the phenomenon that the effect of ordinary infrared image detail enhancement methods is too abrupt, so that the processed infrared image not only has excellent scene detail enhancement capabilities, but also the gray scale distribution is closer to the real scene, which is greatly improved Visual perception of infrared images.

Description

technical field [0001] The invention relates to the technical field of infrared image high dynamic range display, in particular to an intelligent infrared image scene enhancement method. Background technique [0002] Infrared thermal imaging is widely used in military and civilian fields, such as system design, system testing, system manufacturing, chemical imaging, night vision imaging, disaster search and rescue, target recognition and detection, and target tracking. Generally, ordinary infrared cameras have a very wide dynamic range of data, and traditional display devices do not support such a high dynamic range, so when displaying infrared images, the common method is to perform a similar histogram on the infrared image Equalization and other high dynamic range compression techniques. However, the simple histogram equalization technology has extremely limited effect on improving the visual perception of infrared images, and cannot fully express the details in the real ...

AI Technical Summary

Problems solved by technology

In order to overcome this problem, some researchers used Gaussian filters to process strong edges, but due to the incomplete matching of the mathematical model, this "ghost" could not be completely eliminated, which greatly reduced its application in actual engineering. The latter uses a guided linear filter, although it can obtain a good "ghost" elimination effect, but due to the computational efficiency constraints of the linear filter, the final image enhancement effect is average, and it cannot fully highlight all the ghost images in the scene. Small details also limit its application effect in actual engineering

So until now, in the infrared thermal imaging system, there has not been an excellent scene detail enhancement algorithm applied to the engineering machine

Images