Method and device for realizing automatic white balance based on background modeling

Abstract

The invention discloses a method and a device for implementing automatic white balance based on background modeling. The method comprises the steps of carrying out background modeling on an input image; counting white blocks of a background image, and estimating a light source color temperature under the current environment according to a weighted RGB value of the counted white blocks; and carrying out white balance adjustment on the input image based on estimation for the light source color temperature. By adopting the method and the device disclosed by the invention, influences imposed on white balance parameters by a moving object in the scene can be improved, thereby reducing influences imposed on color reproduction by the moving object, thus reducing color drifting of video, and improving visual effects of the video.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a method and device for realizing automatic white balance based on background modeling. Background technique [0002] In the field of video surveillance, for scenes under different color temperature light sources, the color of the image captured by the image sensor usually deviates from the real color. Therefore, in practical applications, the original image data obtained by the image sensor cannot be directly displayed and output. However, an image processing chip is often required to correct the original image data according to the color temperature information of the light source in the current scene, so as to restore the original image data to a true color before finally displaying the output. [0003] White balance processing is one of the correction methods. White balance is aimed at different color temperature conditions, by adjusting the color circuit inside the...

AI Technical Summary

Problems solved by technology

Traditional automatic white balance methods (such as grayscale world algorithm, edge grayscale world algorithm, Rentix algorithm, color gamut mapping algorithm, neural network algorithm, and white balance algorithm based on multi-frame images, etc.) all use the entire image to adjust the color temperature of the light source. It is estimated that in practical applications, moving objects such as vehicles and pedestrians in the scene will often affect the judgment of color temperature, which will cause the color drift of the picture obtained after white balance processing, and then affect the final visual effect

[0004] For example: in some scenes in security monitoring, moving vehicles will account for a large proportion of the entire image, and the color information on the vehicle will also interfere with the estimation of color temperature; in night scenes, many moving targets have their own light sources Yes, if the color temperature is estimated for the panorama, it is obvious that the light source of the moving target will also be counted, which will strongly interfere with the color consistency of the monitoring screen

Images