Modeling method for user quality of experience (QoE) in adaptive point cloud video streaming media

Abstract

The invention discloses a modeling method for the user Quality of Experience (QoE) in adaptive point cloud video streaming media, which comprises the following steps of: 1, collecting an original point cloud video, segmenting the original point cloud video into frame groups in time, then segmenting the original point cloud video into blocks in space, and finally compressing each block into different quality grades; 2, performing quality selection according to user view angle prediction and network bandwidth, and calculating a quality grade of block selection in a user view angle; 3, re-fusing the blocks and the frame groups to obtain a processed point cloud video and pause time and quality switching generated by the processed point cloud video during streaming media transmission; 4, evaluating the objective quality of the processed point cloud video; and 5, carrying out experience quality scoring on the processed point cloud video, and carrying out QoE modeling according to the score, objective quality, pause time and quality switching. According to the method, point cloud video QoE modeling can be carried out more comprehensively, and the subjective experience quality of the user in the point cloud video streaming media can be accurately predicted under the condition that the network bandwidth is changed.

Description

technical field [0001] The invention relates to the field of multimedia video transmission, in particular to a modeling method for user quality of experience (QoE) in adaptive point cloud video streaming media. Background technique [0002] Chen Yiping and others from Xiamen University invented a deep learning-based laser scanning SLAM indoor 3D point cloud quality evaluation method (public number: CN110246112A), including: S1, obtaining high-quality point clouds through laser scanning SLAM devices; S2, evaluating high-quality Degrade the point cloud to obtain the simulated point cloud; S3, perform trajectory measurement analysis on the simulated point cloud; S4, extract the plane from the high-quality point cloud and the simulated point cloud, perform local consistency noise analysis and geometric rule analysis on the plane, and quantify the points Cloud quality; S5, segment the high-quality point cloud and the simulated point cloud to obtain point cloud blocks; S6, normali...

AI Technical Summary

Problems solved by technology

[0007] The present invention is to avoid the disadvantages of the above-mentioned prior art, and to provide a simple and feasible modeling method for user quality of experience QoE in adaptive point cloud video streaming media, in order to perform point cloud video QoE more comprehensively Modeling, accurately predicting the quality of experience of users in point cloud video streaming media under the condition of network bandwidth changes, so as to solve the problem that QoE modeling cannot fully and accurately reflect the quality of user experience

Images