Multi-Viewer Image Adjustment With Gaze-Based Quality Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image adjustment methods for multiple users fail to accurately account for individual viewer interests, leading to frustration when their interests are not in the majority, resulting in a crude and inefficient distribution of computing and bandwidth resources.
Innovation Solution
An image adjustment system that tracks multiple points of attention using gaze estimation to dynamically adjust image quality based on a heatmap of user attention, iteratively adapting quality distribution to enhance user engagement and optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single heat map of attention is created by aggregating all users' focuses of attention, then the overall image quality distribution can be optimized for the majority, but individual users with minority interests experience frustration and reduced viewing quality
Solution Approach 1:
The patent segments users into multiple clusters based on their gaze patterns, creating separate heat maps for each cluster rather than a single aggregated heat map. This allows different image quality distributions to be generated for different user groups, enabling both efficient resource allocation and individualized attention to minority interests.
Solution Approach 2:
The system dynamically switches between different heat maps based on the actual viewer group composition. As users join or leave and their gaze patterns change, the clustering is updated and the appropriate heat map is selected, making the system adaptable to changing viewing conditions and user preferences.
2Loss of energy
If image quality is optimized for the majority focus area, then resource allocation is efficient, but minority user interests are neglected leading to user frustration
Solution Approach 1:
By segmenting users into clusters with similar gaze patterns, the system can allocate bandwidth efficiently to each segment's focus area rather than optimizing for a single majority area. This ensures that minority user interests receive adequate resource allocation while maintaining overall efficiency.
Solution Approach 2:
The system changes the parameter of image quality distribution dynamically based on the identified viewer cluster. Different quality parameters are applied to different heat map regions corresponding to different user groups, ensuring both efficiency and user satisfaction.
3Measurement precision
If gaze tracking is used to detect focus of attention, then individual user interests can be identified, but the system complexity increases when multiple users are involved
Solution Approach 1:
The patent combines multiple users' gaze data into clustered groups rather than processing each user individually. By merging similar gaze patterns into clusters and creating representative heat maps for each cluster, the system reduces computational complexity while maintaining precise detection of focus areas for each user group.
Solution Approach 2:
The clustering mechanism serves multiple functions: it identifies user groups, determines representative focus areas, and selects appropriate heat maps. This multi-functionality reduces overall system complexity by consolidating multiple processing tasks into a unified clustering framework.
Data Source
AI summary
A method of image adjustment for an image sequence, comprises the steps of generating a first estimate, of the gaze positions of multiple viewers of an image, modifying a distribution of image quality for an image, responsive to the first estimate, and providing the image to the multiple viewers, generating a second estimate, of the effect of modifying the distribution of image quality on the gaze positions of at least a subset of viewers, and modifying the distribution of image quality for a subsequent image, responsive to the second estimate.