A dash rate adaptive method based on video content complexity perception
A technology of content complexity and video content, applied in the direction of selective content distribution, image communication, electrical components, etc., can solve the problem of reduced viewing quality for users
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment 1
[0077] A DASH code rate adaptive method based on perception of video content complexity disclosed by the present invention specifically relates to a server and a client. The server is used to perceive the content complexity of the video and mark the content complexity in the MPD file. The client is used to implement bit rate adaptation.
[0078] The present invention specifically comprises the following steps:
[0079] A DASH code rate adaptive method based on video content complexity perception, comprising the following steps:
[0080] Step 1: The server perceives the content complexity of the video, and obtains the content complexity level of each segment in the video;
[0081] Step 11: the server encodes the video according to the MPEG standard to obtain N video versions with different bit rates, and this video is the video that the user wants to watch and needs to be downloaded from the server;
[0082] Step 12: Carry out shot boundary detection on the N video versions, ...
specific Embodiment 2
[0104] This embodiment provides a specific implementation solution based on Embodiment 1.
[0105] A DASH code rate adaptive method based on video content complexity perception, comprising the following steps:
[0106] Step 1: The server encodes the 10-minute video at one end according to the corresponding bit rate in the bit rate set [90, 180, 360, 540, 720, 1080, 1440, 1880] Kbps to obtain 8 different video versions; Shot boundary detection is performed on the 8 video versions, and the detected shot boundaries of different versions of the video are the same; the content complexity perception is performed on the 8 video versions, and the content complexity values of all the shots of the video are clustered by the clustering method as 3 levels, the content complexity level of the same shot in different video versions is the same; the 8 video versions are all sliced by 2 seconds to get the complexity level of each slice, and for slices with more than one shot, select the ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


