Adaptive Camera Triggering Using Sensor Hub User Presence Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile computing devices face battery drain issues due to continuous power consumption from background activities, and existing low-power standby modes cause undesirable delays when waking up, while always-on vision systems consume too much power.
Innovation Solution
Implement a sensor hub-based adaptive triggering system using lower-powered sensors to initiate always-on vision, combining a fixed logic model with a user behavior model for improved accuracy and reduced power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the device maintains continuous background activity and stays powered on, then the device is always ready for use, but battery consumption increases
Solution Approach 1:
The system performs preliminary actions by using low-power sensors to detect user presence and predict wake-up needs before the device is actually needed. The sensor hub continuously monitors sensor data in a low-power state, and when user presence is detected, the device proactively wakes up before the user would need to use it, eliminating wait time while avoiding continuous full-power operation.
2Use of energy by moving object
If the device enters low-power standby mode to conserve battery, then battery life extends, but device wake-up time increases
Solution Approach 1:
The system performs preliminary detection using the sensor hub and machine learning models to predict when the device will be needed. By detecting user presence and analyzing usage patterns before wake-up is required, the device can wake up in advance of actual need, thus eliminating the effective wait time while maintaining low-power standby mode for extended battery life.
Solution Approach 2:
The system dynamically adjusts the wake-up timing based on predicted user needs. Rather than using a fixed wake-up schedule, the machine learning model continuously adapts to user behavior patterns and dynamically determines optimal wake-up times, allowing the device to balance between staying in low-power mode and being ready when needed.
3Ease of operation
If always-on vision is used to detect user presence, then device readiness improves, but power consumption increases
Solution Approach 1:
The system segments the detection function into two parts: a continuous low-power sensor monitoring layer handled by the sensor hub, and an intermittent high-accuracy vision layer activated only when needed. The sensor hub processes sensor data continuously in a low-power state, and only triggers the vision processor when sensor data indicates user presence, thus achieving accurate detection without continuous vision processing power consumption.
Solution Approach 2:
The sensor hub acts as an intermediary between the low-power sensor inputs and the high-power vision processor. It pre-processes sensor data, applies machine learning models to predict user presence, and only activates the vision processor when prediction confidence thresholds are met, thus mediating between continuous monitoring needs and power consumption constraints.
Data Source
AI summary
The present disclosure relates to automatic user adaptive triggering, such as triggering of always-on vision. A camera may be activated based on a result of applying a set of sensor features to a logic model. A label for the set of sensor features may be determined based on whether a face is detected or a face is not detected in a first set of images captured by the camera. The labeled sensor data may be stored along with historical data. A user behavior model may be generated using a learning algorithm based on the labeled sensor data. The user model may be incrementally updated based on new training data. The user behavior model may be used for determining whether to the activate the camera based on a particular set of sensor features.