Predicting Future Fields of View for 360 Video Streaming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In information-centric networks (ICNs), there is a challenge in reducing bandwidth consumption for high-resolution 360-degree video streaming, as traditional methods require transmitting all possible fields of view (FoVs) after the current one, leading to increased network bandwidth usage and potential for low-resolution or frozen video experiences.
Innovation Solution
The method involves predicting future FoVs based on a history of requested FoVs, popular FoVs, and FoV transitions, and caching or prefetching these future FoVs before they are requested, thereby reducing the need to transmit all possible FoVs and optimizing bandwidth usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all possible FoVs are transmitted after the current one, then the video experience reliability is improved, but the network bandwidth consumption increases
Solution Approach 1:
The system performs preliminary actions by predicting future FoVs based on historical user behavior patterns and popularity data before users actually request them. This allows the network to proactively transmit predicted FoVs during idle periods, ensuring high-resolution video experience when users do request them, while avoiding unnecessary transmission of all possible FoVs.
Solution Approach 2:
The system dynamically changes transmission parameters by adjusting which FoVs are transmitted based on prediction confidence levels and user behavior patterns. Instead of transmitting all possible FoVs with equal priority, the system prioritizes transmission of predicted FoVs while reducing or eliminating transmission of unlikely FoVs, optimizing bandwidth usage while maintaining video quality.
2Reliability
If high-resolution video streams are provided, then the viewer experience is improved, but the network bandwidth consumption increases
Solution Approach 1:
The system applies local quality by providing high-resolution video streams selectively for predicted FoVs that users are likely to request, rather than uniformly across all possible FoVs. This allows the network to concentrate bandwidth resources on specific high-priority FoVs while using lower resolution or no transmission for low-priority FoVs, maintaining overall viewer experience quality while reducing total bandwidth consumption.
3Loss of energy
If video streams are cached before requests, then the bandwidth consumption is reduced, but the device complexity increases
Solution Approach 1:
The system implements self-service by using automated machine learning models and algorithms to predict user FoV requests and manage caching decisions without requiring manual configuration or complex rule-based systems. The prediction model automatically learns from historical data and adapts to user behavior patterns, simplifying the overall system architecture while effectively reducing bandwidth consumption through intelligent pre-caching.
Data Source
AI summary
The disclosure relates to technology for providing determined future fields of view (FoVs) of a 360 degree video stream in a network having multiple video streams corresponding to multiple FoVs. FoV interest messages including requests for FoVs at time instants of the video stream are collected from viewers of the stream. A sequence of popular FoVs is created according to the messages, each representing a frequently requested FoV at a distinctive time instant. FoV transitions are created according to the FoV interest messages, each FoV transition including a current FoV a time instant and a next FoV of a next time instant, indicating a likely next FoV to be subsequent requested. Future FoVs of future time instants are determined for a user viewing the video stream with a history of requested FoVs of past time instants, based on the history of requested FoVs, the sequence and the transitions.