GPU-based camera video projection method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a GPU-based camera video projection method and device, equipment and a storage medium. According to the technical scheme provided by the embodiment of the invention, a GPU carries out hard decoding on the video stream returned by the camera to obtain the original video frame; distortion correction is carried out on the original video frame in the GPU basedon the pixel-by-pixel mapping relationship; corrected video frames are obtained, at the moment, the obtained corrected video frame can be transmitted to a rendering pipeline for a video projection process; by adjusting the position and posture of the camera in the three-dimensional scene, the fusion of the video image and the three-dimensional scene is realized, the projection effect of the videois effectively improved, the video data is processed in the GPU in the whole process, multiple copies of the video data between the video memory and the memory are reduced, and the video projection efficiency is greatly improved.

Description

technical field [0001] The embodiments of the present application relate to the field of image processing, and in particular to a GPU-based camera video projection method, device, device, and storage medium. Background technique [0002] The current video projection schemes are all based on the pinhole camera model, that is, the camera is considered to conform to the ideal undistorted pinhole imaging model. During the projection configuration process, by setting the camera's field of view and adjusting the camera's position and posture and other external orientation parameters , so that the relative position and posture of the camera in the three-dimensional digital space is the same as its position and posture in the physical world, so that the perfect fit between the video projection screen and the three-dimensional model can be realized. [0003] However, in actual engineering, cameras often have distortions, especially fisheye and wide-angle cameras. The straight roads i...

AI Technical Summary

Problems solved by technology

[0003] However, in actual engineering, cameras often have distortions, especially fisheye and wide-angle cameras. The straight roads in the video images often turn into curves, and the images need to be corrected before projection. Video decoding, Distortion correction and projection need to process each pixel of each frame of the picture. In the traditional method, whether the video is decoded by software or hardware, the picture will be returned to the memory, and then the distortion correction and projection will be performed. The data exists between the video memory and the memory. The problem of affecting efficiency due to multiple copies between

Images