Gaze Detection Control for Intent-Aware Display Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computing systems struggle to balance predicting user actions with conserving resources, often leading to unnecessary activation of functions or consumption of computational resources due to image-based activity systems, such as facial recognition, which can inadvertently unlock or change display settings based on user presence, regardless of user intent.
Innovation Solution
Utilizing gaze detection to determine user intent by processing images with a neural network model on a neural processing unit, enabling functions only when the user's gaze is directed towards specific regions or elements on the display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If image-based activity systems (e.g., facial recognition) are used to detect user presence, then user authentication and display control can be automated, but the system may inadvertently activate functions or consume resources when the user is merely present rather than intending to interact
Solution Approach 1:
The patent introduces gaze detection as an intermediary mechanism between simple presence detection and function activation. The system first detects user presence via image-based systems, then uses gaze detection to determine if the user is actually looking at the display before activating functions. This intermediary step prevents spurious activations while maintaining automation, as demonstrated when the system correctly ignores users who are merely present in the field-of-view but not gazing at the display.
2Measurement precision
If the system continuously monitors user activity to predict actions, then user intent can be accurately predicted, but computing resources and power are excessively consumed
Solution Approach 1:
The patent implements periodic monitoring rather than continuous monitoring by using inactivity timers that trigger gaze detection only when a user is detected present but no interaction has occurred recently. The system periodically checks for user gaze at display locations to determine if functions should be activated, rather than continuously monitoring all user actions. This reduces power consumption while maintaining accurate intent prediction when needed.
Solution Approach 2:
The system uses the user's own gaze behavior as the triggering mechanism for monitoring. When the user actually gazes at a display location, their gaze itself triggers the more intensive monitoring and function activation processes. This self-service approach ensures resources are only consumed when the user is actively engaging with the system, not when they are merely present.
3Loss of energy
If inactivity timers are used to save power by locking displays or entering screensaver mode, then energy consumption is reduced, but user interaction may be frustrated when the system locks during active viewing
Solution Approach 1:
The patent implements continuous feedback through gaze detection that monitors whether the user is still looking at the display. When the user gazes at the display, the system receives feedback that the user is actively engaged and prevents screensaver activation or locking. When the user looks away, the feedback indicates inactivity and allows the inactivity timer to proceed with power-saving measures. This feedback mechanism eliminates the frustration of unexpected locking during active viewing while maintaining power savings during genuine inactivity.
Data Source
AI summary
Aspects of the present disclosure relate to systems and methods for controlling a function of a computing system using gaze detection. In examples, one or more images of a user are received and gaze information may be determined from the received one or more images. Non-gaze information may be received when the gaze information is determined to satisfy a condition. Accordingly, a function may be enabled based on the received non-gaze information. In examples, the gaze information may be determined by extracting a plurality of features from the received one or more images, providing the plurality of features to a neural network, and determining, utilizing the neural network, a location at a display device at which a gaze of the user is directed.