Light and color homogenizing method and system used among images and considering radiation two-dimensional distribution

Abstract

The invention provides a light and color homogenizing method and system used among images and considering radiation two-dimensional distribution. The method comprises the steps of: carrying out object-level smoothing processing on images to be homogenized so as to removing the targets too bright or too dark in foreground; counting a mean value and a variance, and utilizing the integral statistical parameters to carry out radiation adjustment on each smoothed image; carrying out pre-splicing on the radiation adjustment result and obtaining a reference low-frequency image; carrying out Contourlet conversion, obtaining separated high-frequency and low-frequency parts, utilizing a differential method to carry out radiation adjustment on the low-frequency part, carrying out Contourlet reverse conversion, and obtaining a single image after the radiation adjustment; and carrying out splicing on all images after the radiation adjustment, and obtaining a final spliced image with the light and color homogenizing effect. According to the invention, the method is clear, the operationality is high, the problem of inconsistent brightness tones among the images of different periods is solved, the problem of inconsistent image brightness distribution caused by sensor limits is also solved, and the final image splicing result has a better visual effect.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a method and system for uniform light and color between images in consideration of two-dimensional distribution of radiation. Background technique [0002] Due to different imaging conditions such as acquisition time, illumination, photographing angle, and object types, remote sensing images have uneven brightness distribution, uneven contrast, and inconsistent colors among images, which greatly restricts subsequent orthophotos. Effects of using remote sensing imagery in stitching and other image engineering applications. Color uniformity is the process of eliminating these inhomogeneities between images. Therefore, in order to express the objective real world more accurately and truly, obtain high-quality image information and use it effectively, uniform light and color are very necessary. [0003] In recent years, UAV imaging technology has developed ra...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes a technical solution for uniform light and color between images that takes into account the two-dimensional distribution of radiation. Inconsistent brightness distribution caused by sensor limitations makes the final image stitching results have better visual effects

Images