Method, device, computer equipment and readable medium for determining picture group length

Abstract

The present disclosure provides a method for determining the length of a group of pictures. The method comprises obtaining encoding information, optical flow motion vectors, and feature parameters of a video stream. The method utilizes a preset neural network model to determine the scene to which each pixel of each frame image in the video stream belongs based on the encoding information, motion vectors, and feature parameters. The scene includes at least two preset scenes. The method determines the length of the group of pictures for each frame image in the current judgment scene based on the number of pixels in the image belonging to the current judgment scene and the total number of pixels in the image. If the length of the group of pictures cannot be determined, the length of the group of pictures is determined in the next judgment scene until all preset scenes are traversed. In embodiments of the present disclosure, the length of the group of pictures can change as the video content changes, thereby improving encoding quality and bit rate and reducing the size of the compressed bitstream. The present disclosure also provides a device for determining the length of the group of pictures, a computer device, and a readable medium.

Images