Multi-camera images stitching and color homogenizing method

Abstract

The present invention provides a multi-camera images stitching and color homogenizing method, comprising the following steps of: S1, increasing luminance of each image by using Gamma correction; S2, selecting an image that has greatest image information entropy from the images with increased luminance as a reference image, wherein the remaining picture are target images; S3, transforming each image from an RGB color space to a YCbCr color space; S4, adjusting the color and luminance of the target images to be consistent with those of the reference image in the YCbCr color space by using the reference image as a reference; S5, performing a color space inverse transformation on each image, to obtain images that locate in the RGB space. S6, performing stitching on the images by using an image homonymy points matching algorithm, to obtain a preliminary panorama image; and S7, performing contrast enhancement processing on the obtained preliminary panorama image, to obtain a luminance and color balanced panorama image. The multi-camera images stitching and color homogenizing method of the present invention is simple and quick in calculation method, and can be applied to color homogenizing processing of color images.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a multi-camera image splicing and uniform color method. Background technique [0002] At present, with the rapid development of computer technology and image processing technology, multi-camera image stitching technology has been widely used, such as virtual reality, military security, surveying and mapping, etc. Real-time image stitching generally requires a lot of cameras to acquire video images synchronously, and adjacent images must have a certain overlapping area, and then the image transformation matrix is ​​calculated by image matching method, so as to stitch together images of large scenes. However, due to differences in camera models, imaging performance, viewing angles, and working environment, images from different cameras in the same fusion area will have certain differences in brightness, color, etc. If these video images are directly registered, the entire The splic...

AI Technical Summary

Problems solved by technology

[0006] ①Current color uniformity algorithms mostly use manual selection in the selection of reference images, which is highly subjective and cannot automatically select high-quality reference images;

[0007] ②The current color uniformity algorithm is mainly for gray-scale images, and the uniform light algorithm for gray-scale images is not suitable for color uniformity;

[0008] ③ The overlapping degree of adjacent images is important information in image uniformity. Currently, color uniformity algorithms are often based on direct color matching from the image to be uniformed to the reference image, ignoring the overlapping degree information of adjacent images;

[0009] ④The current color uniformity algorithm has a better color uniformity effect on images with a large contrast between light and dark, but when the contrast in the darker areas of the image is weak, the contrast in these areas is still weak after color uniformity processing

[0010] Aiming at the deficiencies in the current prior art, the purpose of the present invention is to provide a multi-camera image color uniformity method that can adjust the brightness and color inconsistency between multiple images, so that the final stitched panoramic image has balanced brightness and color

Images