Abstract
A computer vision camera sensor module includes an image sensing element, embedded AI processing, and an inertial measurement unit (IMU) to support ultra-low power always-on operation and adaptive device management. The sensor executes AI algorithms locally to analyze visual data and IMU motion data, detect user activity and environmental change, and select among tracking modes including 3-DoF tracking for sedentary activity and 6-DoF tracking for standing or walking. Based on detected meaningful change, the sensor autonomously maintains other device sensors or cameras in standby or triggers their activation, while avoiding wake-up of a backend processor for decision-making. The module may be co-packaged with an AI chip to reduce device footprint. Applications include smart glasses, AR/VR headsets, wearables, security cameras, and robotics.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Anonymous, "Computer Vision Camera Sensor with Embedded AI Features and IMU for Ultra-Low Power Adaptive Device Management", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/10711