Related Experiment Video
Updated: Dec 30, 2025
03:56
A View of Their Own: Capturing the Egocentric View of Infants and Toddlers with Head-Mounted Cameras
Published on: October 5, 2018
7.9K
Orientation-Based Food Image Capture for Head Mounted Egocentric Camera.
Summary
This study introduces an efficient method for wearable food intake monitoring. By capturing images only during head tilts associated with eating, it reduces power consumption and extends battery life for the device.
Area of Science:
- Biomedical Engineering
- Wearable Technology
- Nutritional Science
Background:
- Current head-mounted wearable sensors for food intake monitoring use multiple sensors, leading to high power consumption.
- Periodic image capture by these devices results in many irrelevant images, draining battery life.
Purpose of the Study:
- To develop an efficient food image capture method for wearable sensors.
- To reduce power consumption and improve battery life in food intake monitoring devices.
Main Methods:
- Utilized 3D accelerometer data to estimate head tilt angles.
- Developed a classifier using curve fitting on head tilt angles to trigger image capture.
- Validated the method with 15 volunteers in a free-living environment over extended periods.
Main Results:
- The proposed method achieved a sensitivity of 0.97 for predicting food image capture.
- Specificity for predicting food image capture was 0.47.
- Demonstrated potential for significant improvement in wearable device battery life.
Conclusions:
- An efficient, head-tilt-angle-triggered image capture system can enhance wearable food intake monitoring.
- This approach optimizes power usage by capturing relevant images only when needed.
- The method shows promise for practical, long-term use of wearable dietary assessment tools.
