Method and device for generating indoor panoramic video

Abstract

The embodiment of the present invention discloses a method and device for generating indoor panoramic video. For each frame of fisheye video image, the coordinates of each pixel of the fisheye video image in the image coordinate system are converted into coordinates of the spherical coordinate system, Obtain a fisheye hemisphere image based on the spherical coordinate system; determine the view volume parameters of each of the N view texture maps corresponding to the fisheye hemisphere image according to the shape of the preset room, and determine the view volume parameters of each view texture map according to the N view textures The viewing volume parameters of each perspective texture map in the figure, the N perspective texture maps corresponding to the fisheye hemisphere map are obtained, and the N perspective texture maps are rendered to the N surfaces inside the preset living room to generate The panoramic video image corresponding to the fisheye video image. It can be seen that this solution can generate panoramic video images showing a three-dimensional effect; it does not use complex image stitching algorithms, which improves the real-time performance of panoramic video generation; does not require multiple cameras or aerial cameras, and the cost of shooting equipment is low.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a method and device for generating indoor panoramic video. Background technique [0002] With the continuous development of science and technology, panoramic video has exerted great value and advantages in many fields. For example: in a video surveillance system, when monitoring indoor scenes, such as monitoring a supermarket, the camera collects video images to generate a panoramic video to achieve better monitoring effects. [0003] Currently, there are several methods for generating panoramic videos: [0004] 1. The same scene is shot from different angles, and the obtained video images are stitched into a sphere using an image stitching algorithm. With this method, multiple cameras or an aerial camera are required, the cost of the shooting equipment is high, and the image stitching algorithm is complicated, and the real-time performance of the panoramic video is po...

AI Technical Summary

Problems solved by technology

Using this method, what is unfolded through PTZ is still a two-dimensional image, which is not much different from the traditional video viewing effect, and the user experience is poor.

Images