InFlightAI Computer Vision Model
Graffiti Detection
AI Model Overview
InFlightAI’s Graffiti Detection model uses computer vision AI to identify graffiti, tagging, and unauthorized markings on walls, equipment, and infrastructure. It supports rapid remediation workflows, helps maintain property appearance, and reduces the long-term visibility and cost of vandalism.
Markings are recognized by how they differ from the underlying surface in color, edge and pattern. Detection runs on the live feed during the patrol.
Tagging is flagged within a patrol cycle, when removal is cheapest and repeat tagging least likely. Facilities work from a located, dated record instead of a complaint-driven queue.
How It Works
Graffiti Detection returns segmentation mask output. It identifies graffiti and tagging along with other unauthorized markings on walls, equipment and infrastructure.
Graffiti 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 after the flight has landed, once imagery and waypoint data have been synced to the platform. The model is ready from day one, with no site-specific configuration required.