InFlightAI Computer Vision Model
Thermal Person Detection
AI Model Overview
InFlightAI’s Thermal Person Detection model uses thermal imaging AI to detect human presence in low-light or no-light conditions. It enhances security coverage and reliability in challenging environments where traditional vision systems are limited.
Detection works from a person’s heat signature rather than their outline, so darkness, smoke and glare don’t defeat it. Where both are available, thermal runs alongside visual imagery, which improves accuracy over either alone. A thermal-capable payload is required.
People are detected in conditions where standard cameras fail outright. Reliable patrol coverage extends to night shift without adding lighting infrastructure.
How It Works
Thermal Person Detection returns bounding box output. It identifies human presence by heat signature, including people in low-light and no-light conditions and those obscured by smoke or glare.
Thermal Person Detection is a physical security patrol model, currently deployed across industries like Electric Utilities, Oil & Gas, Manufacturing, Logistics, Power Generation, Nuclear and Mining. Detections are returned in real time while the flight is still in the air, so alerts reach the team before the aircraft lands. The model is ready from day one, with no site-specific configuration required.