STMicroelectronics presents a new Human Presence Detection (HPD) solution for laptops, PCs, monitors, and accessories that improves security and privacy while reducing power usage by more than 20% daily.
ST’s proprietary technology offers a number of advantages, including a longer battery life and user privacy or wellness notifications, by fusing industry-leading FlightSense Time-of-Flight (ToF) sensors with special AI algorithms to provide hands-free, quick Windows Hello authentication.
The 5th generation turnkey ST solution
The new ST HPD solution, which combines hardware and software components by design, is a readily deployable system based on the FlightSense 8×8 multizones Time-of-Flight sensor (VL53L8CP) and enhanced by proprietary AI-based algorithms that enable features like head orientation tracking, multi-person detection, and human presence detection.
For OEMs, this integration produces a special ready-to-use solution that doesn’t require any more development.
Advanced capabilities including hand posture recognition, gesture identification, and wellness monitoring via human posture analysis are also integrated with this fifth generation of sensors.
ST’s Human Presence Detection (HPD) solution enables enhanced features such as:
- Adaptive Screen Dimming tracks head orientation to dim the screen when the user isn’t looking, reducing power consumption by more than 20%.
- Walk-Away Lock & Wake-on-Attention automatically locks the device when the user leaves and wakes up upon return, improving security and convenience.
- Multi-Person Detection alerts the user if someone is looking over their shoulder, enhancing privacy.
Tailored AI algorithm
Data collecting, labeling, cleaning, AI training, and integration into a mass-market product are all steps in STMicroelectronics’ extensive AI-based development process.
In order to continuously improve AI algorithms, this endeavor drew on thousands of data-logs from various sources, including contributions from employees who submitted their own seating and movement data over a period of many months.
The conversion of a Proof-Of-Concept (PoC) into a mature solution that can identify the head orientation of a laptop user using just 8×8 pixels of distance data is one noteworthy accomplishment.
Four worldwide data collection campaigns, 25 solution releases spanning a year, and strict quality control of AI training data were all part of the painstaking development process that led to this result.
The strategy also included the creation of four specialized AI networks: Presence AI, HOR (Head Orientation) AI, Posture AI, and Hand Posture AI, as well as a customized pre-processing technique for VL53L8CP range data. This achievement was made possible in large part by the VL53L8CP ToF sensor, which was designed to maximize the Signal-To-Noise ratio (SNR) per zone.
Enhanced user experience & privacy protection
The ToF sensor ensures complete user privacy without capturing images or relying on the camera, unlike previous versions of webcam-based solutions.
Adaptive Screen Dimming:
- Uses AI algorithms to analyze the user’s head orientation. If the user is not looking at the screen, the system gradually dims the display to conserve power.
- Extends battery life by minimizing energy consumption.
- Optimizes for low power consumption with AI algorithms and can be seamlessly integrated into existing PC sensor hubs.
Walk-Away Lock (WAL) & Wake-on-Approach (WOA):
- The ToF sensor automatically locks the PC when the user moves away and wakes it upon their return, eliminating the need for manual interaction.
- This feature enhances security, safeguards sensitive data, and offers a seamless, hands-free user experience.
- Advanced filtering algorithms help prevent false triggers, ensuring the system remains unaffected by casual passerby.
Multi-Person Detection (MPD):
- The system detects multiple people in front of the screen and alerts the user if someone is looking over their shoulder.
- Enhances privacy by preventing unauthorized viewing of sensitive information.
- Advanced algorithms enable the system to differentiate between the primary user and other nearby individuals.
Leadership Comments
“Building on the integration of ST FlightSense technology in more than 260 laptops and PC models launched in recent years, we are looking forward to see our new HPD solution contributing to make devices more energy-efficient, secure, and user-friendly,” said Alexandre Balmefrezol, Executive Vice President and General Manager of the Imaging Sub-Group at STMicroelectronics. “As AI and sensor technology continue to advance, with greater integration of both hardware and software, we can expect to see even more sophisticated and intuitive ways of interacting with our devices, and ST is best positioned to continue to lead this market trend.”
“Since 2023, 3D sensing in consumer applications has gained new momentum, driven by the demand for better user experiences, safety, personal robotics, spatial computing, and enhanced photography and streaming. Time-of-Flight (ToF) technology is expanding beyond smartphones and tablets into drones, robots, AR/VR headsets, home projectors, and laptops. In 2024, ToF modules generated $2.2 billion in revenue, with projections reaching $3.8 billion by 2030 (9.5% CAGR). Compact and affordable, multizone dToF sensors are now emerging to enhance laptop experiences and enable new use cases,” said Florian Domengie, PhD Principal Analyst, Imaging at Yole Group.
Technical highlights: VL53L8CP: ST FlightSense 8×8 multizones ToF sensor. https://www.st.com/en/imaging-and-photonics-solutions/time-of-flight-sensors.html
- AI-based: compact, low-power algorithms suitable for integration into PC sensor hubs.
- A complete ready-to-use solution includes hardware (ToF sensor) and software (AI algorithms).
