In-home 3D sensor system to spot falls without wearables
Using Structured Light Sensing with Machine Learning to Detect Unwitnessed In-Home Falls
This project builds a small, unobtrusive 3D sensor and smart software to automatically detect when older adults fall at home and trigger alerts when they cannot use a wearable button.
Quick facts
| Grant type | Sbir 2 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Applied Universal Dynamics Corporation NIH-funded |
| Lab location | 1 site (Loretto, United States) |
| Project ID | NIH-11177677 on NIH RePORTER |
What this research studies
From my perspective as someone living at home, this system uses a structured light 3D sensor that makes a point-cloud picture of a room and machine learning that learns the motion patterns of falls. The device sits quietly in the home and does not require me to wear anything or push a button. When the software detects a likely fall, it can send an alert so help can arrive sooner. The project builds on earlier (phase I) tests and focuses on making the system reliable, low-cost, and easy to install in real homes.
Who could benefit from this research
Good fit: Ideal candidates are adults aged 65 or older, especially those living alone or with mild to moderate memory problems who may forget to wear or press emergency pendants.
Not a fit: People who live in nursing homes or assisted-living facilities with existing monitored systems, or those who do not want in-home sensors for privacy reasons, may not benefit from this system.
Why it matters
Potential benefit: If successful, the system could get help to fallen older adults faster, reducing complications from long periods on the floor and possibly lowering injury-related costs.
How similar studies have performed: Related camera- and depth-sensor fall-detection projects have shown promising results in lab and limited home pilots, but large-scale, real-world in-home testing is still fairly limited.
Where this research is happening
Loretto, United States
- Applied Universal Dynamics Corporation — Loretto, United States (Active)
Researchers
- Principal investigator: Gibson, Paul — Applied Universal Dynamics Corporation
- Study coordinator: Gibson, Paul
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.