Panoramic Video Quality Assessment Based on Non-Local Spherical CNN

Abstract

Panoramic video and stereoscopic panoramic video are essential carriers of virtual reality content, so it is very crucial to establish their quality assessment models for the standardization of virtual reality industry. However, it is very challenging to evaluate the quality of the panoramic video at present. One reason is that the spatial information of the panoramic video is warped due to the projection process, and the conventional video quality assessment (VQA) method is difficult to deal with this problem. Another reason is that the traditional VQA method is problematic to capture the complex global time information in the panoramic video. In response to the above questions, this paper presents an end-to-end neural network model to evaluate the quality of panoramic video and stereoscopic panoramic video. Compared to other panoramic video quality assessment methods, our proposed method combines spherical convolutional neural networks (CNN) and non-local neural networks, which can effectively extract complex spatiotemporal information of the panoramic video. We evaluate the method in two databases, VRQ-TJU and VR-VQA48. Experiments show the effectiveness of different modules in our method, and our method outperforms state-of-the-art other related methods.

[Retracted] Deep Learning‐Based Multitarget Motion Shadow Rejection and Accurate Tracking for Sports Video

“…e detection module is the most time-consuming and important, and the multiobjective optimization of the detection module is of utmost importance. It is important to ensure the accuracy of the detection module for target detection and to reduce the time required for the detection module as much as possible [27][28][29]. Firstly, each target to be tracked is determined based on the sports video multitarget motion of each target using the detection region optimization algorithm from the previous chapter and corrected for prediction separately.…”

[Retracted] Simulation of Tennis Match Scene Classification Algorithm Based on Adaptive Gaussian Mixture Model Parameter Estimation

“…However, this improved method has two shortcomings: first, when the number of frames is small, the background extracted by multiframe averaging is good, but as the number of frames increases, this background extraction algorithm is less effective, and second, when the number of frames is large, it greatly increases the time complexity of the program. Other researchers use the statistical histogram-based background extraction algorithm as the background initialization model for vision-based background modelling methods [21][22][23][24][25][26][27]. e shortcoming of this improvement is that the background extraction is good when in simple scenes, but for variable scenes, the background image extracted by this algorithm contains a lot of noise, resulting in still poor target detection results.…”

[Retracted] Mobile Internet of Things Dynamic Grid QoS Service Matching Mechanism and Simulation Analysis

“…With the gradual popularity of mobile Internet applications and the continuous improvement of mobile search applications, when users need to query some urgently needed, they will increasingly tend to use mobile search [29][30][31][32][33][34]. e structure of the mobile grid system is shown in Figure 1, which is mainly composed of three modules: a fixed grid site, a mobile terminal group, and a middleware mobile gateway.…”