Dynamic Video Configurations Memory Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding systems experience delays and degraded quality when switching between different codec configurations during video coding sessions, as they require reconfiguration and memory reallocation, which can cause interruptions in video delivery.
Innovation Solution
The system negotiates multiple codec configurations and estimates the largest size of decoded picture buffers, allocating memory accordingly to avoid reallocations and interruptions, allowing seamless switching between configurations without disrupting video delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional reconfiguration and reset of video sequence is performed when switching codec configurations, then coding parameters can be revised to meet changing video characteristics, but this causes long delay and degraded quality at the switchover point
Solution Approach 1:
The system performs preliminary actions by pre-negotiating multiple codec configurations and pre-allocating memory buffers for all possible configurations before switching occurs. This allows the decoder to immediately switch between configurations without reconfiguration delays, as all necessary resources are already prepared and allocated.
2Speed
If multiple video encoder/decoder instances are created to handle different configurations, then switching speed among configurations is improved, but memory consumption increases significantly
Solution Approach 1:
The system implements a universal buffer that can serve multiple codec configurations simultaneously. Instead of creating separate decoder instances for each configuration, a single decoder with a multi-configurable buffer can handle different resolutions, profiles, and other parameters by reconfiguring the same buffer resources, thereby reducing overall memory consumption while maintaining fast switching capability.
Solution Approach 2:
The patent merges multiple configuration-specific buffers into a single unified buffer structure that can be dynamically allocated to different configurations as needed. This consolidation eliminates redundant memory allocations across multiple decoder instances while preserving the ability to switch between configurations rapidly.
3Adaptability or versatility
If codec configuration changes are implemented during video coding sessions, then encoding can better meet changing video characteristics, but interruptions in video delivery occur
Solution Approach 1:
The system performs preliminary negotiation and memory allocation for multiple codec configurations before actual switching occurs. This pre-preparation ensures that when configuration changes are needed during video delivery, the decoder can immediately switch to the pre-configured settings without interruptions, maintaining continuous video playback.
Data Source
AI summary
Techniques are disclosed for managing memory allocations when coding video data according to multiple codec configurations. According to these techniques, devices may negotiate parameters of a coding session that include parameters of a plurality of different codec configurations that may be used during the coding session. A device may estimate sizes of decoded picture buffers for each of the negotiated codec configurations and allocate in its memory a portion of memory sized according to a largest size of the estimated decoded picture buffers. Thereafter, the devices may exchange coded video data. The exchange may involve decoding coded data of reference pictures and storing the decoded reference pictures in the allocated memory. During the coding session, the devices may toggle among the different negotiated codec configurations. As they do, reallocations of memory may be avoided.