Video quality evaluation method based on deep learning and server
A technology of video quality and deep learning, applied in the field of deep learning, can solve problems such as the inability to realize video quality adjustment, fast and accurate evaluation of video and other multimedia, and achieve fast and accurate video quality evaluation and the effect of improving video quality
Active Publication Date: 2019-08-16
FUZHOU ROCKCHIP SEMICON
View PDF8 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] To this end, it is necessary to provide a video quality evaluation method and server based on deep learning to solve the problem that existing video and other multimedia cannot achieve fast and accurate evaluation and video quality adjustment.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] In order to explain in detail the technical content, structural features, achieved goals and effects of the technical solution, the following will be described in detail in conjunction with specific embodiments and accompanying drawings.
[0045] see Figure 1 to Figure 4 , this embodiment provides a video quality evaluation method based on deep learning, which can be applied to a video server. The video server is used to send the video stream to a video terminal connected thereto, and the video terminal is used to display the video. It includes the following steps: step S101 loads the deep learning model used for video quality evaluation; step S102 calculates the video quality score of the current terminal in real time according to the deep learning model; step S103 calculates the bandwidth of the current terminal in real time; step S104 loads the video quality dynamic balance Strategy, the dynamic balancing strategy is a balancing strategy between video parameters, vi...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a video quality evaluation method based on deep learning and a server. The method comprises the following steps of loading a deep learning model for video quality evaluation; calculating the video quality score of a current terminal in real time according to the deep learning model; calculating the bandwidth of the current terminal in real time; loading a video quality dynamic equalization strategy, wherein the dynamic equalization strategy is an equalization strategy among the video parameters, the video quality score and the bandwidth; and dynamically redistributing the video parameters according to the dynamic equalization strategy. According to the technical scheme, the video quality can be calculated in real time according to the deep learning model, then the rapid and accurate video quality evaluation can be achieved, and the dynamic adjustment of the terminal video can be achieved according to the equalization strategy, and therefore the terminal video quality is improved.
Description
technical field [0001] The invention relates to the technical field of deep learning, in particular to a video quality evaluation method and server based on deep learning. Background technique [0002] With the popularity of 4G communication networks and smart phones, the mobile Internet leads the development of the Internet. The main traffic carried by the Internet is no longer text and audio, but streaming video, live broadcast services, online education, video conferencing, etc. If the video encoding parameters of the encoder (H264 / H265 / VP9, etc.) are set improperly, the video will be distorted. The phenomenon of video distortion is reflected in block effect (Blocking), blur effect (Blurring) and ringing effect (Ringing). Video quality evaluation and real-time monitoring of streaming media services are problems to be solved urgently. At present, the industry generally has the following typical practices: using expert experience and theoretical calculations as the basis...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/24H04L29/06
CPCH04L41/145H04L65/80H04L41/044H04L41/0823H04L41/0896H04L65/75
Inventor 洪涛程明传
Owner FUZHOU ROCKCHIP SEMICON