Autonomous Mobile Device User Engagement Tracking via Face Orientation and Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing devices lack the ability to accurately determine user engagement levels with autonomous mobile devices, leading to suboptimal interaction and content delivery, especially in multi-user scenarios where engagement varies.
Innovation Solution
An autonomous mobile device (AMD) uses image data and sensors to calculate a user engagement score based on face orientation, distance, and confidence values, employing neural networks and Gaussian functions to assess user engagement and adjust device operations accordingly, such as content presentation and movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the AMD uses image data and sensors to calculate user engagement score, then user engagement tracking accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the user engagement assessment into multiple independent attributes (face orientation, distance, confidence values) that are calculated separately and then combined. This modular approach improves measurement precision while managing device complexity by breaking down the complex task into manageable components.
Solution Approach 2:
The system transitions from binary engagement detection to multi-dimensional engagement scoring by incorporating multiple attributes (face orientation angles, distance measurements, confidence values) that provide a more nuanced and accurate representation of user engagement levels.
2Ease of operation
If the AMD adjusts operations based on real-time engagement levels, then user experience is improved, but computational requirements increase
Solution Approach 1:
The system pre-defines engagement thresholds and corresponding device response rules before runtime. When engagement scores are calculated, the system simply compares scores against pre-established thresholds and executes predetermined actions, significantly reducing real-time computational requirements while maintaining responsive user experience adjustments.
Solution Approach 2:
The system adjusts device operational parameters (such as content delivery, device movement, or presentation settings) based on engagement score thresholds, enabling dynamic adaptation to user needs while using efficient parameter-based control rather than complex real-time optimization algorithms.
3Measurement precision
If the AMD uses multiple attributes to determine engagement score, then engagement assessment accuracy is improved, but processing time increases
Solution Approach 1:
The system calculates each engagement attribute (face orientation, distance, confidence) independently using specialized algorithms optimized for that specific measurement, then combines them using a weighted formula. This segmentation allows parallel processing of attributes and reduces overall processing time compared to a monolithic approach.
Solution Approach 2:
The system implements confidence value thresholds that allow it to occasionally skip calculating certain attributes when confidence is already sufficient, or to use approximate calculations in low-power modes, balancing accuracy requirements with processing time constraints based on current operational context.
Data Source
AI summary
An autonomous mobile device (AMD) or other device may perform various tasks during operation. The AMD includes a camera to acquire an image. Some tasks, such as presenting information on a display screen or a video call, may involve the AMD determining whether a user is engaged with the AMD. The AMD may move a component, such as the camera or the display screen, to provide a best experience for an engaged user. Images from the camera are processed to determine attributes of the user, such as yaw of the face of the user, pitch of the face of the user, distance from the camera, and so forth. Based on the values of these attributes, a user engagement score is determined. The score may be used to select a particular user from many users in the image, or to otherwise facilitate operation of the AMD.