Eye Tracking Activation Maps for Sensor Data Subsampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional artificial reality systems face challenges in capturing and processing high-resolution real-world content efficiently due to significant time and power consumption, making them unsuitable for power-constrained real-time applications.
Innovation Solution
A computer-implemented method that determines eye gaze direction to generate activation maps for sensor data acquisition, allowing for varying sampling densities, and processes sensor data by sub-sampling or binning based on these maps to reduce computational load and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-resolution real-world content is captured uniformly across the entire field of view, then image quality is improved, but time consumption and power consumption increase significantly
Solution Approach 1:
The patent applies local quality by capturing high-resolution content only in the foveal region (where the user is looking) and lower-resolution content in peripheral regions. This is achieved through eye-tracking to identify the foveal region, then configuring the imaging sensor to capture detailed data only in that specific area while reducing resolution elsewhere, thereby maintaining overall image quality where it matters most while reducing time consumption.
Solution Approach 2:
The patent segments the field of view into multiple regions based on eye-gaze data: a central foveal region requiring high resolution and peripheral regions accepting lower resolution. This segmentation allows the system to apply different capture strategies to different parts of the scene, optimizing the balance between image quality and processing time by treating each region according to its importance.
2Measurement precision
If high-resolution real-world content is captured uniformly across the entire field of view, then image quality is improved, but power consumption increases significantly
Solution Approach 1:
The system captures high-resolution content locally only in the foveal region identified through eye-tracking, while capturing lower-resolution content in peripheral regions. This localized high-quality capture reduces the total amount of data processed and transmitted, thereby reducing power consumption while maintaining image quality in the visually critical foveal area.
Solution Approach 2:
The patent segments the imaging area into foveal and peripheral regions, applying different resolution settings to each segment. This segmentation reduces the overall computational load and data transmission requirements, directly reducing power consumption while preserving image quality where the user is actually looking.
3Measurement precision
If real-world content is captured at high resolution, then image quality is improved, but processing time increases due to computational complexity
Solution Approach 1:
The patent processes high-resolution image data only for the foveal region while using lower-resolution data for peripheral regions. This selective processing based on local quality requirements significantly reduces the total computational workload and processing time, while maintaining high image quality in the visually important foveal area where detailed processing is most beneficial.
Solution Approach 2:
The patent segments the processing workload by region, applying computationally intensive processing only to the foveal region and simpler processing to peripheral regions. This segmentation of processing tasks reduces overall computational complexity and processing time while preserving image quality where it matters most to the user experience.
Data Source
AI summary
Eye gaze data is generated by an eye-tracking module. One or more activation maps are generated by a sensing module based on the eye gaze data. The sensing module acquires sensor data based on the one or more activation maps.