Eye-Tracking Subframe Processing for Workload Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current eye-tracking technologies face challenges in reducing operating workload and power consumption, as they often require processing full frames of data from eye and scene cameras, leading to increased computation time and energy usage.
Innovation Solution
The method involves capturing and processing sub-frames from eye and scene cameras, using object detection and region of interest techniques to extract relevant data, reducing the data amount and thereby lowering power consumption and computation time, while estimating the eyeball position through back projection or approximation operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If full frames from eye and scene cameras are processed, then measurement precision is maintained, but operating workload and power consumption increase
Solution Approach 1:
The patent divides the full image frames into multiple sub-frames (e.g., quadrants or regions) and processes only selected sub-frames containing the eye region. This segmentation reduces the total data volume processed while maintaining measurement precision by focusing computational resources on relevant areas.
Solution Approach 2:
The patent extracts only the necessary eye-related data from the full frames by identifying and processing specific regions of interest (sub-frames) rather than analyzing complete frames. This extraction approach maintains measurement accuracy for eyeball position while significantly reducing power consumption.
2Measurement precision
If full frames from eye and scene cameras are processed, then measurement precision is maintained, but computation time increases
Solution Approach 1:
The patent segments full frames into smaller sub-frames and processes only those containing eye information. This reduces computation time by limiting processing to essential regions while preserving measurement precision through targeted analysis of eye-containing sub-frames.
Solution Approach 2:
The patent applies partial action by processing only a subset of sub-frames rather than complete frames. This approach achieves sufficient measurement precision for eyeball position estimation without the excessive computation time required for full-frame processing.
3Use of energy by moving object
If sub-frames are used instead of full frames, then power consumption is reduced, but data completeness may be compromised
Solution Approach 1:
The patent extracts only the essential eye-related information from frames by processing selected sub-frames. This extraction maintains data completeness for eyeball position estimation while reducing power consumption by excluding irrelevant data from processing.
Solution Approach 2:
The patent applies local quality by assigning different processing priorities to different regions. Sub-frames containing eye information are processed with high priority to maintain data completeness, while other regions are excluded or processed minimally to reduce power consumption.
Data Source
AI summary
Eye-tracking methods and devices are provided for reducing operating workload. One sub frame of an eye frame and/or a scene frame is used to estimate the eyeball position. Such an approach can reduce operating workload and power consumption.