Senecta Book a demo

Research

Research on fall detection with thermal sensing and AI

What we measure, published. We test the AI behind our pods on public data and in a real, lived-in room, and we publish the papers, including the numbers that are not good enough yet.

Papers

Preprint · October 2026

Asking a Multimodal LLM Whether Someone Fell: Zero-Shot Screening of Low-Resolution Thermal Video in a Laboratory and an Occupied Home

Marcos Junca and Mauro Junca, Senecta Inc.

Can a general-purpose AI model, with no training, tell from a low-resolution thermal sensor (heat only, no ordinary camera) whether someone fell? We asked Google's Gemini exactly as our research prototype does, on 438 hand-located staged falls from a public thermal dataset and on every clip the prototype produced over 76 hours of ordinary life in a lived-in room, and we compared it with detectors trained the conventional way.

  • No false alarms in ordinary life. Over 76 hours of everyday activity in a lived-in room the AI made no false fall calls, and it called none of the 499 laboratory clips of people walking, sitting, lying on the floor and getting up a fall.
  • It catches most falls it can see, not all. It caught 69% of the staged falls of people it had never seen in a public thermal dataset, and 4 of 9 staged falls the camera could see in the room.
  • One sentence of instructions made a large difference. A cautionary line telling the AI that a person who goes out of view has not fallen cost about 14 points of fall sensitivity on the same laboratory falls (69% with it, 83% without it).
Read the summary Full paper (PDF)

In progress

Thermal or video: what does an AI lose, and what does a person keep private?

We are testing whether the same AI judges falls as well from thermal video as from normal video of the same moments, and how much less a thermal image tells it about who the person is. The pass mark was written down and committed before we saw any of the video.

Honest scope

  • The falls were staged, by younger adults, in one laboratory and one room. Real falls of older people are different.
  • The room recordings come from a research prototype, not the product's final sensor, mounting or software.
  • These are research results, not a promise of how often a product will catch a fall. No system catches every fall.

Senecta makes the pods described in this research, so these are our own studies, not independent evaluations. Each paper describes its methods, its data and every limitation we know of.