Cloud-dependent
Streaming audio and video off the car burns power, raises privacy questions, and stops working the moment connectivity does.
VMS — by GPI International
On-device detection for the vehicle body.
A low-power embedded system that detects and classifies physical events on and around a vehicle in real time — impacts, someone leaning or sitting on the car, sustained contact, scratches, breaking glass — and reports them through a companion app.
Why it exists
The damage nobody sees happen is the damage nobody can prove.
Vehicles are exposed, and detection has been stuck between three bad options.
Power-hungry
Continuous AI inference drains the battery, which is incompatible with monitoring a car that is parked — the situation that matters most.
False alarms
Naïve sensors fire on passing music, slamming doors and road vibration. Alerts that cry wolf stop being read.
Signal and noise
It catches what matters, and ignores the rest.
The second column is the harder engineering problem. A detector that catches everything is easy; one that stays quiet through ordinary life is not.
Detected
- Kick, punch or impactA high-energy strike on a body panel.
- A person sitting or leaning on the carSustained presence and weight on the body.
- Sustained contact near the bumperProlonged manual contact with the surface.
- ScratchingHigh-frequency rubbing along the paint.
- Breaking glassThe acoustic signature of a window going in.
Suppressed
- Loud music nearbyAnother vehicle's radio.
- Ground vibrationPeople walking or jumping close to the car.
- Adjacent car doorsOpening and closing beside you.
- Construction noiseAmbient site noise around the vehicle.
- Background noiseOrdinary sound, all day, every day.
How it works
Four stages, all of them on the device.
Sense
Microphones and an accelerometer capture the raw signal from the body of the car.
Extract
A small set of discriminative features is computed continuously from that signal.
Sniff
A low-power gate flags anomalies and rejects the obvious, without waking anything expensive.
Classify
A neural stage names the event and returns a confidence, locally, with no round trip.
The gate is the whole trick
An ultra low-power stage watches the sensors continuously and decides the exact moment to wake the full AI pipeline. The expensive part sleeps until there is a reason not to — which is what makes always-on monitoring possible on a battery.
Private by construction, not by policy
All processing happens on the microcontroller. No audio leaves the vehicle, and nothing depends on a connection being available. Models can be improved over the air without changing any hardware.
The data behind it
Performance is bought with data, so we built the machine that produces it.
An automated 360° test rig runs reproducible interactions across a whole vehicle and labels every session into training-ready data — configurable by zone, material, duration and intensity.
Reproducible by design
The same event, in the same place, at the same intensity, as many times as it takes. That is what separates a dataset from a collection of recordings.
Day-in-the-life recording
Long stretches of ordinary vehicle life — parked, driving, day, night, every season. It is what makes the suppression figures credible rather than optimistic.
Performance
Where it is, and where it is going.
Demo figures are measured. Production figures are targets, and are labelled as such — a number without its conditions is not a number.
| Event | Demo, measured | Production target |
|---|---|---|
| Kick or punch to a surface | >80% | >95% |
| Person sits on the hood | >80% | >95% |
| Contact near the bumper | >80% | >95% |
| Window smash | >80% | >95% |
| Scratch | >80% | >95% |
Design goals for the production system: disturber suppression above 90%, an always-on sensing budget under 1 mA, and classification within 500 ms of an event beginning.
Where it applies
One multi-sensor core, four markets.
OEM automotive
Design-win driven, with functional-safety expectations and factory integration. The deepest and highest-value path.
Aftermarket
Retrofit-friendly and fast to market. Lower integration depth, price-sensitive channels, the quickest route to a fielded product.
Insurance & fleet
Verified event data for claims validation and risk pricing — as much a data service as a sensor.
Industrial & surveillance
The same core in adjacent applications, with different environmental and certification constraints.
Want to see it work?
We can walk through the architecture, the data engine and where it stands today.