Video Sub-Picture Partitioning for Balanced Multi-Core Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding standards like HEVC do not effectively balance pixel rates across multiple processing cores, leading to uneven workload distribution and sub-optimal throughput in multi-core architectures.
Innovation Solution
Divide video pictures into independently decodable sub-pictures, ensuring each sub-picture contains an approximately equal number of LCUs, and signal this partitioning in the compressed bit stream to facilitate balanced pixel rate distribution across multiple processing cores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If video pictures are processed as single units on multiple processing cores, then processing can be parallelized, but workload distribution becomes uneven leading to sub-optimal throughput
Solution Approach 1:
The patent divides a video picture into multiple independently decodable sub-pictures, where each sub-picture contains a specific region of the original picture. This segmentation allows each processing core to handle one sub-picture independently, creating balanced workload distribution across multiple cores while maintaining parallel processing capability, thereby resolving the contradiction between throughput and workload distribution
2Ease of operation
If video pictures are divided into sub-pictures for parallel processing, then workload balancing improves, but picture decoding independence may be compromised
Solution Approach 1:
The patent segments the picture into sub-pictures with carefully managed dependencies. Each sub-picture is assigned to a specific processing core with minimal inter-core dependencies, allowing independent decoding while maintaining overall picture coherence. This approach preserves decoding independence across cores while achieving workload balance
3Adaptability or versatility
If unequal sized sub-pictures are created for partitioning, then processing flexibility increases, but pixel rate balancing across cores deteriorates
Solution Approach 1:
The patent applies local quality by creating sub-pictures with approximately equal numbers of LCUs (Largest Coding Units) distributed across different regions of the picture. This ensures that each processing core receives a balanced workload in terms of pixel rate, while the overall picture structure and coding flexibility are maintained through adaptive sub-picture partitioning
Data Source
AI summary
A method for decoding a compressed video bit stream in a video decoder to recover a video sequence, the video decoder including a plurality of decoder processing cores is provided. The method includes determining that a picture is encoded in the compressed bit stream as a pre-determined number of independently encoded sub-pictures, and dispatching a first encoded sub-picture of the pre-determined number of sub-pictures to a first decoder processing core of the plurality of decoder processing cores and a second encoded sub-picture of the pre-determined number of sub-pictures to a second decoder processing core of the plurality of decoder processing cores, wherein the first encoded sub-picture and the second encoded sub-picture are independently decoded in parallel on the respective first and second decoder processing cores.