Insights

Camera-based SAT or inductive loops?

Published on by the Omnivias team at Omnicog Tecnologia.

An inductive loop measures vehicle passage at one point in the pavement; a camera with computer vision measures volume, class, axles, speed and density from the CCTV that already exists, with no roadworks. In many projects the camera replaces the loop; where specific metrological requirements apply, the two methods work together.

Two ways to do SAT

In the terminology of ARTESP, the São Paulo state transport regulator, and ANTT, the federal one, SAT is the automatic traffic sensor (Sensor Automático de Tráfego): the equipment that counts and classifies vehicles by lane and records speed. For a long time, that meant an inductive loop cut into the pavement. Omnivias SAT performs the same function with the highway’s cameras, using computer vision.

Inductive loop and camera-based SAT, side by side
DimensionInductive loopCamera-based SAT (Omnivias)
InstallationPavement cutting and lane closureUses existing CCTV; no roadworks
What it measuresPassage, occupancy and speed at the loop pointVolume, class, axles, speed and V85, density, headway and HCM parameters
Visual contextNoneThe image shows what happened and allows the count to be audited
MaintenanceWears with the pavement; resurfacing requires reinstallationRemote updates and calibration
IncidentsDoes not detect themThe same camera feeds DAI
Adverse conditionsLittle affected by light and rainCalibrated per camera for night, rain and reflections
ValidationDepends on sensor and installationComparison against the reference agreed in the field

When the camera replaces the loop

When the camera frames the lanes well, is stable and has enough light at night, computer vision delivers counts by class continuously. In Omnivias projects in production, counting accuracy runs above 95% against the reference agreed in the field.

When to use both

At points with specific metrological requirements, such as weighing or enforcement, or when the contract calls for certified equipment in the pavement, the loop stays. The camera adds visual classification, an auditable time series and incident detection at the same point.

Classified volumetric counting

This is the count broken down by vehicle class, lane, direction and period. The classes follow what the contract or the regulator calls for (cars, trucks by number of axles, buses, motorcycles), and SAT delivers reports with calculation records.

See also: SAT, the camera checklist and the glossary.

Frequently asked questions

Does the camera replace the inductive loop for counting?

In many projects, yes. Computer vision produces counts, classification, speed and other data with no sensors in the pavement. Where specific metrological requirements apply, the two methods work side by side.

Is SAT an automatic traffic sensor or a Traffic Analysis System?

Both. In ARTESP and ANTT terminology, SAT is the automatic traffic sensor (Sensor Automático de Tráfego). Omnivias calls its product a camera-based Traffic Analysis System because, beyond counting, it measures density, V85 and HCM parameters.

How accurate is camera-based counting?

In Omnivias projects in production, counting accuracy runs above 95% against the reference agreed in the field. The acceptance criterion is defined per project before going live.

Can the camera count axles?

Yes, in technically validated scenes: it depends on the camera angle and the distance to the lane.

Start with a pilot on your own cameras

First we assess the cameras the highway already has; then a proof of concept using footage from the road section itself shows the measured result. Depending on the size of the project, the assessment and the proof of concept can be free of charge, and the proof of concept starts running within 10 days of signing the agreement.

  1. Assessment

    Resolution, position, coverage, lighting and network of the existing cameras, against what the operation wants to measure and detect.

  2. Proof of concept

    SAT and DAI running on footage from the road section itself, measured against the agreed success criteria.

  3. Production

    On-premises, cloud or hybrid architecture, control center integration, rules, alerts and reports.

  4. Continuous calibration

    Rules and models tuned camera by camera using the real alert history.

WhatsApp