Vehicle all-round panorama generation method and device, equipment and storage medium

Abstract

The invention relates to the field of image processing, in particular to a vehicle all-round panorama generation method and device, equipment and a storage medium. The method comprises the following steps: performing projection transformation on images shot by each camera to obtain aerial view of each image to the ground; determining an overlapping region in each aerial view; respectively extracting the brightness of each color channel from the overlapping region of each aerial view, and calculating the brightness ratio of single color channels in the overlapping region of the aerial views corresponding to the adjacent cameras; calculating a brightness adjustment coefficient of each color channel of each overlapping region according to the brightness ratio, and adjusting the brightness of the corresponding color channel of the corresponding aerial view according to the brightness adjustment coefficient; and splicing the adjacent aerial views after brightness adjustment to generate an all-round panorama. According to the embodiment of the invention, the brightness of each aerial view can be efficiently and properly adjusted, distortion with the original image is avoided, and the brightness tone of the original image is kept.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a method, device, device and storage medium for generating a panoramic view of a vehicle. Background technique [0002] At present, the surround view panoramic system has been popularized on many mass-produced models. The key to this system is to effectively splice images from different cameras and eliminate seams and brightness differences in the images. [0003] In the currently published patents, the methods generally include: de-distorting the images of each camera separately, projecting and transforming them into a bird's-eye view of the ground, and then stitching them together. Due to the different exposure of each camera, the brightness of the stitched panorama is generally unbalanced, and brightness balance adjustment is required. The existing adjustment method uses a complex brightness compensation function, which is difficult to ensure the real-time fluency of th...

AI Technical Summary

Problems solved by technology

Due to the different exposure of each camera, the brightness of the stitched panorama is generally unbalanced, and brightness balance adjustment is required. The existing adjustment method uses a complex brightness compensation function, which is difficult to guarantee the real-time fluency of the system; moreover, only considering The overall brightness is consistent, but there is a large distortion with the original image

Images