Head-Mounted Camera ROI Windowing for Low-Power Facial Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing head-mounted systems for tracking facial expressions, such as AR/VR headsets, face challenges in efficiently managing power consumption due to the need for continuous data collection and processing over extended periods, especially in untethered, battery-operated devices.
Innovation Solution
Implementing a region of interest (ROI) windowing technique for a head-mounted camera that dynamically adjusts its focus based on the relevance of facial landmarks, using different binning values and resolutions for power-efficient facial expression detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous data collection and processing is performed for facial expression tracking, then tracking accuracy is maintained, but power consumption increases
Solution Approach 1:
The patent divides the facial region into multiple zones of interest (ZOIs) based on facial expression relevance. Instead of processing the entire face uniformly, the system segments the facial area and selectively processes only the relevant ZOIs, reducing computational load and power consumption while maintaining tracking accuracy for critical facial regions.
Solution Approach 2:
The system dynamically adjusts the set of active zones of interest based on detected facial expressions. When certain expressions are detected, the system activates or deactivates specific ZOIs accordingly, allowing continuous adaptation to changing facial states while optimizing power consumption by processing only necessary regions at any given time.
2Loss of information
If the camera sensor processes the entire facial region, then comprehensive facial data is captured, but computation load increases
Solution Approach 1:
The patent applies different processing qualities to different facial regions by defining multiple zones of interest with varying levels of detail. Each ZOI is processed according to its specific importance for facial expression analysis, allowing the system to maintain high data quality for critical regions while reducing computation for less critical areas, thereby optimizing the balance between information completeness and computational complexity.
3Measurement precision
If the camera reads at high resolution, then facial landmark detection precision is improved, but power consumption increases
Solution Approach 1:
The system applies partial action by reading camera data at high resolution only for the specific zones of interest rather than the entire facial region. This allows the system to maintain high measurement precision for critical facial landmarks while reducing overall power consumption by limiting high-resolution processing to only the necessary portions of the face.
Data Source
AI summary
System and method that utilize windowing for efficient capturing of facial landmarks include an inward-facing head-mounted camera that captures images of a region on a user's face utilizing a sensor supporting changing of its region of interest (ROI). The system also includes a computer that detects, based on the images, a type of facial expression expressed by the user, which belongs to a group comprising first and second facial expressions. Responsive to detecting that the user expresses the first facial expression, the computer reads from the camera a first ROI that covers a first subset of facial landmarks relevant to the first facial expression. Responsive to detecting that the user expresses the second facial expression, the computer reads from the camera a second ROI that covers a second subset of facial landmarks relevant to the second facial expression, with the first and second ROIs being different.