Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

Back to your search

AI-Powered Rail Traffic Detection and Classification

Mobility · Safety & Security · Planning & Decision-making

What it collects

About a place
Anonymized data
  • Images and video captured by in situ cameras installed along rail lines across North America, recording train movements at specific track locations.
Operational data
Anonymized data
  • Training data includes images of various railcar types and dangerous goods (DG) placards used to build the classification model. At runtime, the system also processes contextual data about train composition and network activity.
Run by
Transport Canada (TC)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization
Your copy
You cannot see the data it holds about you. What you can do

What it is for

MobilitySafety & SecurityPlanning & Decision-making

RailState is a data platform used by Transport Canada to monitor rail traffic across North America in real time. It uses cameras and AI to detect, count, and classify train movements, including identifying railcar types and dangerous goods placards. The system supports government employees in tracking network performance and responding to disruptions — it does not involve personal information about members of the public.

What it collects and what happens to it

Data taken in

About a place
Anonymized data
  • Images and video captured by in situ cameras installed along rail lines across North America, recording train movements at specific track locations.
Operational data
Anonymized data
  • Training data includes images of various railcar types and dangerous goods (DG) placards used to build the classification model. At runtime, the system also processes contextual data about train composition and network activity.

Processing

Computer Vision
  • Image and object recognition algorithms process camera feeds to detect train presence, segment individual railcars, create panoramic compositions of full trains, and classify car types and DG placards.
Classification & Prediction
  • Classifies railcar types when a car identifier cannot be read optically, and predicts performance trends from historical and real-time movement data.

What it does

Sensing (Perceptive AI)
Autonomous
  • Uses in situ cameras to capture images of passing trains and autonomously detects train presence, counts cars, and extracts structured detections for downstream classification.
Deciding (Analytical AI)
Human decides
  • Classifies detected railcars into types (including dangerous goods placard identification) and scores/counts train movements, producing structured labels and counts that government employees use for decision-making.

Outputs

About a place
Anonymized data
  • Real-time and historical data on train movements at specific rail network locations across North America, including counts, classifications, and panoramic views of train consists.
Operational data
Anonymized data
  • Network activity summaries, performance trend reports, and situational awareness data during disruptions — consumed by Transport Canada government employees.

Run by

Transport Canada (TC)
  • Federal department accountable for the deployment of RailState to monitor rail network activity and performance across North America.

Government of Canada AI Register — RailState

Built by

Rail State
  • Vendor that builds and supplies the RailState platform, including the camera-based train detector and AI classification capabilities.

Government of Canada AI Register — RailState

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • Output data — train movement records, classifications, and network performance trends — is available to Transport Canada government employees (GC employees) as the primary users.
Not available to me
  • The system does not involve personal information and its outputs are intended for government operational use; the data is not accessible to members of the public.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

The Helpful Places has not listed specific rights for this system.

Risks and safeguards

No risks or safeguards have been published for this system yet.