InFlightAI Computer Vision Model
Person Detection
AI Model Overview
InFlightAI’s Person Detection model uses real-time computer vision AI to identify and count individuals within a scene. It supports live monitoring, occupancy tracking, and security workflows across facilities and perimeters.
People are detected and counted from the live feed, with position reported within the scene. The model works on standard visual imagery; Thermal Person Detection covers low and no-light conditions.
Areas that should be clear get a count and a location, as do areas that should be occupied and aren’t. Occupancy and exclusion-zone checks run without someone watching a monitor, which extends coverage to cameras nobody is assigned to.
How It Works
Person Detection returns bounding box output. It identifies the presence and count of individuals in a scene, people in restricted or off-limits areas, and the absence of people where presence is expected.
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.