Fire and Smoke Detection in a Space Too Big to Sense
A smoke detector has to wait for smoke to reach it. In a concourse, a warehouse, a tunnel, or an open yard that can take minutes. A camera sees the smoke where it starts.
The Capability
Vision-Based Detection across Large Areas
FireTrack provides early fire and smoke detection across indoor and outdoor scenes. Its advantage over point sensing is geometric: it detects fire and smoke in large areas long before traditional smoke detectors or sprinkler systems can react, because it does not wait for the products of combustion to travel to a sensor.
The module was rebuilt on a new architecture to improve detection quality, and it shares the same alerting path as the rest of the platform: crime centers, dispatch, and the Sover secure messenger, with the triggering frame attached so an operator can verify in seconds rather than dispatching on a maybe.
Fire and smoke is also one of the conditions StreamVLM™ prompt detectors are designed to unify, which matters where a site has an unusual variant of the problem that a fixed detector was not built for.
In Operation
Where Point Sensors Do Not Reach
Concourses, Tunnels, Yards, and Perimeters
The places fire detection is hardest are the places IREX already has cameras: transport hubs, critical-infrastructure sites, storage yards, and open perimeters. Detection runs continuously on those streams, with no additional sensing hardware to install and maintain.
FAQ
Does this replace our fire-alarm system?
No. IREX products are expressly not life-saving or emergency systems, and IREX does not warrant that they will prevent loss, damage, or injury. Vision-based detection is an early-warning layer that complements a certified fire-detection system, not a substitute for one.
Why is it faster than a smoke detector?
Because it does not wait for smoke to travel. A point sensor detects combustion products that reach it; a camera sees them where they originate, which in a large or open space is minutes earlier.
Can it handle steam, dust, or exhaust?
Those are the classic false-positive sources, and they are why the module was rebuilt on a new architecture and why each detector carries a confidence threshold and an alert cooldown. Thresholds are tuned on your own scenes during the pilot.
What camera quality does it need?
Any camera that supports ONVIF or streams RTSP with H.264 or H.265 on a static IP can be connected, but connection is not the bar. Each module sets its own resolution, mount position, height, and angle-of-view requirements in the camera requirements, the flagship modules need higher-resolution imagery of the scene than a bare stream, and the recommended primary stream is 1920 × 1080 or 1920 × 1440. A site survey confirms every camera against the module it will run.
Does this run on its own or does someone have to watch it?
It runs on its own and alerts a person. Detections are signals for a human to verify: no response runs autonomously, and the verification and decision are logged against the same Case ID as the detection.
Point It at Your Hardest Space
The loading yard, the tunnel, the concourse. Wherever your current detection is slowest is where this is worth measuring.