Infrared image heterogeneity correction method based on trilateral filtering and a neural network

Abstract

The invention discloses an infrared image heterogeneity correction method based on trilateral filtering and a neural network. The original infrared image of the nth frame in the original infrared image sequence is sequentially loaded as the current frame image, and the corrected gray value of the i-th row and the j-th column of the current frame image is determined, and the n-th frame of infraredimage processingis original through the fast three-edge filtering algorithm; the expected value qn(x) of the pixel x is obtained according to the deviation between the expected value of the i-th row j-th column pixel x of the current frame image and the corrected gray value of the i-th row j-th column pixel, the adaptive iterative step size is updated to obtain the n+1th frame of the original infrared image, the pixel gain parameter and the pixel offset parameter of the corresponding position of the pixel in the i-th row and the j-th column, the original infrared image of the n+1th frame is corrected by the pixel gain parameter and the pixel offset parameter. According to the method, the learning rate of parameters can be improved, and the non-uniformity correction effect of the image canbe improved.

Description

technical field [0001] The invention belongs to the field of infrared image processing, and in particular relates to an infrared image non-uniformity correction method based on a trilateral filter and a neural network. Background technique [0002] As the core component of the infrared imaging system, due to the limitations of manufacturing level and device materials, each pixel of the detector cannot ideally output exactly the same response value under the same irradiance. It is called the non-uniformity of the infrared image. Since the non-uniformity of infrared images is manifested as fixed pattern noise on the image, which seriously affects the quality of infrared images, it is necessary to study the non-uniformity correction algorithm of infrared images. [0003] At present, many scholars have conducted in-depth research on non-uniformity correction technology, and proposed a variety of non-uniformity correction algorithms, which can be mainly divided into two categori...

AI Technical Summary

Problems solved by technology

However, the traditional neural network correction algorithm has the problem of "ghosting" and image degradation

[0004] In order to solve these problems, Vera et al. proposed an adaptive step size algorithm (ALR) on the basis of NN-NUC, which can suppress part of the "ghost", but still has more non-uniformity; in order to better protect the edge Information, Rossi et al. used the bilateral filtering algorithm (BF-NN-NUC) to calculate the expected value, which improved the edge blur and "ghosting" problems to a certain extent, but would destroy the details of non-step edges; in order to make up for this shortcoming, Li Jia et al. used the trilateral filtering algorithm (TF-NN-NUC) to retain more detailed information, but the algorithm took a long time

Images