Infrared enhancement method based on gradient histogram

Abstract

The invention discloses an infrared enhancement method based on a gradient histogram, and the method comprises the following steps: S1, obtaining original infrared data DI, and carrying out the intelligent filtering processing of the original infrared data, and obtaining filtered data BI; S2, establishing a two-dimensional gradient map GI of the filtered image data BI according to the definition of the gradient; S3, calculating an average gradient Mean G and a maximum gradient MaxG of the two-dimensional gradient map GI, and calculating a platform threshold ThresP according to the average gradient; S4, counting a gradient histogram H smaller than the average gradient Mean G according to the two-dimensional gradient map GI; and S5, carrying out platform limitation on the gradient histogram according to the platform threshold value, and then carrying out equalization processing on the gradient histogram. According to the method, the characteristic that the human vision system is more sensitive to the gradient intensity is fully considered, the quality of the infrared image can be effectively improved, and the method is particularly embodied in the aspects of contrast increase, noise suppression and excessive enhancement prevention.

Description

technical field [0001] The invention relates to the field of infrared image processing, in particular to an infrared enhancement method based on a gradient histogram. Background technique [0002] Infrared image enhancement plays an important role in the visual understanding methods of night vision images, and it also plays an important role in the fields of machine vision and artificial intelligence. The output images of modern infrared imaging systems usually have a high dynamic range, while commonly used display devices can only display 256 gray levels. When HDR images are linearly displayed on commonly used display devices, problems such as low contrast, loss of information and blurred details will occur. Infrared equipment can obtain infrared data with a high dynamic range through thermal imaging technology, with a bit width of more than 14 bits. But the human eye can only distinguish the gray scale range of 128 levels, and the gray scale dynamic range of most display...

AI Technical Summary

Problems solved by technology

However, the problem of low contrast, high noise, poor adaptability, and edge burrs has not been completely solved in this solution.

Images