Vehicle-mounted image pixel adjustment method, device and equipment and readable storage medium

Abstract

The invention relates to the field of intelligent driving, and discloses a vehicle-mounted image pixel adjustment method, device and equipment and a readable storage medium. The method comprises the steps: obtaining a to-be-spliced image; calculating the maximum value of the to-be-spliced image in a preset range, and obtaining the brightness value of the image in combination with the filtering operation; carrying out remapping processing on the obtained image brightness value; obtaining a first time sequence overlapping region of the to-be-spliced image, and converting an RGB color space of the first time sequence overlapping region into a YCrCb color space; obtaining the pixel value of each channel of the color space on the two to-be-spliced images in the first time sequence overlapping region, calculating the pixel value error, constructing an error model, and calculating the adjustment coefficient of each color channel based on the error model; adjusting the pixel intensity value ofeach channel according to the adjustment coefficient to obtain a second time sequence overlapping region; and converting the image of the second time sequence overlapping region back to the RGB colorspace, and performing image stitching on the to-be-stitched image according to a multi-band image fusion method to obtain a panoramic image. According to the invention, the inconsistency of splicingpositions is eliminated.

Description

technical field [0001] The present invention relates to the field of intelligent driving, in particular to a vehicle image pixel adjustment method, device, equipment and readable storage medium. Background technique [0002] At present, terminal images are collected through multiple videos in the vehicle, and image stitching and fusion technologies are used to obtain surround-view images around the vehicle. [0003] The method and system for adjusting the consistency of mosaic panorama disclosed in the application number 201210407083.7 first obtains the mosaic of each image to be stitched in the panoramic field of view, and the mosaic includes a reference mosaic, and then establishes other mosaics and the reference mosaic Then calculate the gray scaling factor and offset factor of each other mosaic relative to the reference mosaic, and then adjust the brightness of each pixel of the corresponding mosaic according to the obtained scaling factor and offset factor, The adjustm...

AI Technical Summary

Problems solved by technology

Due to factors such as the movement of the vehicle, the weather for shooting, and the conditions of the camera itself, the multiple video images obtained often have great differences in color and brightness. The panoramic images stitched using these video data, in many cases, the image quality is not high. , splicing marks are obvious

Images