Detail-based partially selective mapping infrared image enhancement method

Abstract

The present invention relates to a detail-based partially selective mapping infrared image enhancement method which mainly includes four steps: image detail acquisition, detail-based fast segmentation, scene judgment and scene-based mapping, and local histogram interpolation splicing, which can effective compress the useless gray range, making the contrast of the entire image enhanced and effectively improving the contrast of the target of interest while maintaining the background of the natural consistency.

Description

technical field [0001] The invention relates to the technical field of visual enhancement of infrared images, which improves the visual perception of images by increasing the contrast of infrared images. Background technique [0002] Currently commonly used infrared image dynamic range compression and contrast enhancement algorithms are mainly divided into two categories, namely linear mapping and nonlinear mapping methods. The linear mapping algorithm is simple, but in the case of a wide dynamic range, the proportion of invalid gray levels is large, resulting in fewer effective gray levels after mapping, which greatly loses detailed information; among nonlinear mapping methods, the most representative The most significant is the histogram equalization algorithm, which can effectively compress the gray level distribution range of the image gray level probability distribution function (PDF) and enhance the contrast of PDF at the same time. The small target or detailed textur...

AI Technical Summary

Problems solved by technology

The linear mapping algorithm is simple, but in the case of a wide dynamic range, the proportion of invalid gray levels is large, resulting in fewer effective gray levels after mapping, which greatly loses detailed information; among nonlinear mapping methods, the most representative The most significant is the histogram equalization algorithm, which can effectively compress the gray level distribution range of the image gray level probability distribution function (PDF) and enhance the contrast of PDF at the same time. The small target or detailed texture features composed of high-value pixels cannot be effectively enhanced, and the noise information of the image is also improved while the contrast is enhanced, making the noise more obvious; the local histogram equalization algorithm can further improve the image quality. The contrast of small and medium objects, but the algorithm will produce obvious edges at the edge of the small window and destroy the overall sense of the image

Images