Visual AI for Asset Maintenance Inspections and Physical Site Security

AI Inspection Model Library

Our InFlightAI models have been trained on real world data, and are currently deployed in the field creating value for enterprise-scale customers around the world.

Sight Glass Reading

InFlightAI Computer Vision Model

Sight Glass Reading

AI Model Overview

InFlightAI’s Sight Glass Reading model uses AI to automatically read liquid levels in cylindrical and glass tube sight glasses, including circular “bullseye” gauges. It ensures oil levels remain within defined operational thresholds and supports horizontal level detection for accurate monitoring.

An ensemble of vision techniques reads the liquid line rather than relying on a single measurement. Common sight glass types are covered by the existing configuration library and read from day one; less common designs are configured for your site during onboarding. Consistent lighting and clear contrast between fluid and glass are needed for a reliable read.

Fluid level is confirmed inside operating range on every pass. Slow loss is caught — the kind that any single reading would look perfectly fine against.

How It Works

Sight Glass Reading returns digitized level output. It reads liquid level in circular “bullseye” sight glasses as well as cylindrical and glass tube designs, measuring against defined operating thresholds and supporting horizontal level lines.

Sight Glass Reading is an asset maintenance 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.

Inspection Type:
Asset Maintenance
Inference Time:
Post Flight
Deployment Window:
Day 1