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

Abstract

The embodiment of the present application discloses a GPU-based camera video projection method, device, device, and storage medium. In the technical solution provided by the embodiment of the present application, the video stream returned by the camera is hard-decoded by the GPU to obtain the original video frame, and the distortion correction is performed on the original video frame in the GPU based on the pixel-by-pixel mapping relationship to obtain the corrected video frame. At this time, The corrected video frame can be transmitted to the rendering pipeline for the video projection process. By adjusting the position and posture of the camera in the 3D scene, the fusion of the video picture and the 3D scene can be realized, which can effectively improve the video projection effect, and the video data is processed in the GPU throughout the process. Reduce multiple copies of video data between video memory and internal memory, greatly improving the efficiency of video projection.

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