ToF Wake-on-Attention Sensing for False Wake-Up Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Human Presence Detection (HPD) systems in electronic devices struggle to distinguish between intended user interactions and non-engagement scenarios, leading to unnecessary power consumption and potential system wear due to false wake-ups.
Innovation Solution
A time-of-flight (ToF) sensor system integrated with neural networks to detect user posture and head orientation, transitioning the device from a low-power mode to a normal mode only when the user is actively engaged.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If HPD system activates device on user presence detection, then user experience is enhanced and system responsiveness is improved, but false wake-up rate increases leading to unnecessary power consumption
Solution Approach 1:
The HPD system is segmented into multiple detection stages: initial presence detection using ToF sensor, followed by posture estimation using first neural network, then head orientation estimation using second neural network. This multi-stage segmentation allows the system to progressively filter out false wake-ups while maintaining responsiveness to genuine user interactions.
Solution Approach 2:
The system changes detection parameters dynamically by analyzing multiple parameters including distance to user, posture characteristics, head orientation angles, and signal quality metrics. By monitoring changes in these parameters over time and combining them through neural networks, the system can distinguish between genuine user engagement and false presence scenarios, reducing unnecessary wake-ups and power consumption.
2Device complexity
If HPD system uses simple presence detection, then implementation complexity is reduced, but ability to distinguish intended interactions from non-engagement scenarios deteriorates
Solution Approach 1:
The system transitions from simple 2D presence detection to 3D spatial understanding by utilizing ToF sensor depth information and implementing two sequential neural networks that analyze posture and head orientation in three-dimensional space. This dimensional enhancement allows precise differentiation between genuine engagement and false presence without proportionally increasing implementation complexity, as the additional dimensional analysis is performed through optimized neural network architectures.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances user experience by ensuring devices wake up only when intended, reducing power consumption and wear by minimizing false activations.
Implementation Method 1
a time-of-flight (ToF) sensor integrated with neural networks to detect user posture and head orientation
Data Source
Figure 1~3
Figure 2
Figure 4
AI summary
According to an embodiment, a method includes collecting, by a time-of-flight (ToF) sensor, real time raw data of a scene comprising a user in its field of view; generating, by a first neural network, an estimate of a posture of the user based on a distance calculated to the user; generating, by a second neural network and in response to determining that the estimate of the posture of the user meets a first criterion, an estimate of a head orientation of the user based on the distance, a standard deviation of the distance, the number of photons returning per unit of time, a standard deviation of the signal value, and a reflection value; and transitioning from low-power to normal mode in response to determining that the user is actively engaged with the device based on the estimate of the head orientation of the user.