Get Started#

This guide walks you through setting up and running the Smart Tolling application:

  • Install and launch the full application stack using the provided setup scripts.

  • Verify it is running by checking vehicle detections, dashboards, and events.

  • Learn where to change configuration (cameras, videos, scene data) for your own setup.

Important

This application ships without sample videos or scene data — see Bring Your Own Data for what to prepare before you start.

Need help running this application? Contact transportation.us@intel.com and we will help you get set up.

Prerequisites#

Before you begin, ensure the following:

  • System Requirements: Verify that the system meets the minimum requirements.

  • Docker Installation Complete: Install Docker. For installation instructions, see Get Docker.

  • Your Own Videos and Scene Data Ready: See Bring Your Own Data for the files you need to prepare.

Setup Guide#

1. Deploy the Source Code#

If you want to clone a specific release branch, replace main with the desired tag. To learn more on partial cloning, check the Repository Cloning guide.

Clone the suite to your Edge Server:

git clone --filter=blob:none --sparse --branch main https://github.com/open-edge-platform/metro-ai-suite.git
cd metro-ai-suite
git sparse-checkout set metro-vision-ai-app-recipe/
cd metro-vision-ai-app-recipe/

2. Configure the Environment#

Verify the variables in .env match your camera RTSP endpoints.

3. Create the .yml File#

Generate the docker-compose.yml file:

./install.sh smart-tolling

4. Launch Services#

Start the application stack using Docker Compose:

export SUPASS=$(cat ./smart-tolling/src/secrets/supass)
docker compose up -d

To stop the application:

docker compose down -v

5. Verify Deployment#

Check the status of all containers:

docker compose ps

Accessing the Application#

Open a browser and go to the following endpoints. The application uses a self-signed HTTPS certificate, so your browser will show a security warning — use Google Chrome and accept it. After starting the stack, wait about a minute for the MQTT broker to come up before the UI shows live data.

Note

Passwords stored in secret files (e.g., supass, influxdb2-admin-token) are under ./smart-tolling/src/secrets/ (Docker).

Scenescape Web UI#

  • URL: https://localhost

  • Username: admin

  • Password: Stored in ./smart-tolling/src/secrets/supass

Scenescape Web UI showing the toll scene, cameras and regions

The example above shows 4 of the 6 camera streams running live at ~30 FPS, using the test videos used during development.

Grafana UI#

Node-RED UI#

  • URL: https://localhost/nodered/

  • Username: <your_nodered_username> (Check ./smart-tolling/src/secrets/nodered/nodered-admin-username)

  • Password: <your_nodered_password> (Check ./smart-tolling/src/secrets/nodered/nodered-admin-password)

InfluxDB UI#

  • URL: http://localhost:8086

  • Username: Stored in ./smart-tolling/src/secrets/influxdb2/influxdb2-admin-username

  • Password: Stored in ./smart-tolling/src/secrets/influxdb2/influxdb2-admin-password