Research Article
Quality Assessment for Networked Video Streaming Based on Deep Learning
@INPROCEEDINGS{10.1007/978-3-030-14657-3_10, author={Jinkun Guo and Shuai Wan}, title={Quality Assessment for Networked Video Streaming Based on Deep Learning}, proceedings={IoT as a Service. 4th EAI International Conference, IoTaaS 2018, Xi’an, China, November 17--18, 2018, Proceedings}, proceedings_a={IOTAAS}, year={2019}, month={3}, keywords={Video quality assessment Deep learning Video streaming}, doi={10.1007/978-3-030-14657-3_10} }- Jinkun Guo
Shuai Wan
Year: 2019
Quality Assessment for Networked Video Streaming Based on Deep Learning
IOTAAS
Springer
DOI: 10.1007/978-3-030-14657-3_10
Abstract
There arises the need for quality assessment in networked video streaming since video services have great significance for both users and providers. In this paper, a neural network is proposed to realize networked video streaming quality assessment. Firstly the key parameters of video streaming are extracted, including the bit-rate, the coded bits of each frames, the number of lost packet and so on. Then the neural network is built to study the mapping of these parameters and video quality. The influence on the video quality assessment by different network depth and different layer settings in the neural network is also taken into comparison. The performance of the proposed neural network has been compared with other methods and evaluated by the quality assessment experiment of videos in different resolutions. The results demonstrate the effectiveness and efficiency of video quality assessment based on the neural network.
