Video Quality Assessment Using Sub-Region Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video quality assessment methods struggle to accurately assess video quality in consideration of a region of interest, leading to inconsistent and time-consuming subjective assessments, and limited effectiveness of objective methods in real-time applications.
Innovation Solution
An electronic device equipped with a processor that executes instructions to obtain subjective assessment scores for sub-regions of a video frame using a first neural network, predicts location weights for these sub-regions using a second neural network, and calculates a final quality score by weighting the subjective assessment scores with the location weights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If subjective quality assessment method is used, then image quality perception characteristics of humans are best reflected, but assessment value differs for each person, it takes a lot of time and is costly
Solution Approach 1:
The video frame is divided into multiple sub-regions, and quality assessment is performed separately for each sub-region. This segmentation allows the system to focus computational resources on specific areas of interest rather than processing the entire frame uniformly, thereby reducing overall assessment time while maintaining perception accuracy.
Solution Approach 2:
Different location weights are assigned to different sub-regions based on their importance to human perception. Regions that are more critical for quality assessment (such as central regions or regions with important content) are given higher weights, while less important regions receive lower weights. This local quality approach improves measurement precision by focusing on perceptually significant areas.
2Measurement precision
If subjective quality assessment method is used, then image quality perception characteristics of humans are best reflected, but it is costly
Solution Approach 1:
By segmenting the video frame into sub-regions and performing quality assessment on each sub-region separately, the system reduces the overall computational cost and time required for assessment while maintaining the accuracy of human perception characteristics.
Solution Approach 2:
The location weight mechanism assigns different importance levels to different sub-regions, allowing the system to concentrate computational resources on perceptually critical regions. This reduces the overall computational burden and cost while preserving measurement precision for important areas.
3Adaptability or versatility
If no-reference quality assessment method is used, then quality measurement can be performed in any application, but assessment accuracy is limited without reference image information
Solution Approach 1:
The patent introduces location weights that reflect the importance of different sub-regions to human perception. By weighting the quality scores of different sub-regions according to their perceptual significance, the system compensates for the lack of reference image information and improves overall assessment accuracy while maintaining the versatility of no-reference methods.
Data Source
AI summary
An electronic device is provided. The electronic device includes a memory storing one or more instructions, and a processor configured to execute the one or more instruction stored in the memory. The processor is configured to execute the one or more instructions to obtain a subjective assessment score for each of a plurality of sub-regions included in an input frame, the subjective assessment score being a Mean Opinion Score (MOS); obtain a location weight for each of the plurality of sub-regions, the location weight indicating characteristics according to a location of a display; obtain a weighted assessment score for each of the plurality of sub-regions, based on the subjective assessment score for each of the plurality of sub-regions and the location weight for each of the plurality of sub-regions; and obtain a final quality score for the entire video frame, based on the weighted assessment score for each of the plurality of sub-regions.