Skip to main content

Plate Recognizer VisionAlert On-premises

The VisionAlert Docker image runs VisionAlert in your own environment so that camera snapshots never leave your network. A single container includes the web dashboard, the API, the anomaly scheduler, and a built-in SFTP server that cameras upload snapshots to.

To use it, get a VisionAlert On-premises license from the VisionAlert page in your Plate Recognizer account, or contact us. An internet connection is required during installation and for periodic license validation.

note

The on-premises edition currently supports cameras that push snapshots over SFTP. Direct integrations with Cisco Meraki, Nx Witness, and OpenEye are only available in VisionAlert Cloud.

Install​

  1. Install Docker on your machine. See the system requirements.

  2. Install VisionAlert using the Manual steps.

  3. Connect your cameras over SFTP and open the dashboard.

Upgrade​

Your data is stored in the /user-data volume, so upgrading replaces only the container.

  1. Stop and remove the container with docker rm -f vision-alert. The vision-alert-data volume is not affected.
  2. Update the image: docker pull platerecognizer/vision-alert.
  3. Run the container (see last step of Installation).
caution

Back up the /user-data volume before upgrading so you can roll back if needed. See Data and Storage.

System Requirements​

Run the container on a 64-bit x86 (amd64) Linux server or virtual machine. No GPU is required. Camera health checks run on the CPU.

Minimum requirements:

  • A 64-bit x86 Linux OS that supports Docker. See the installation guide.
  • 2 CPU cores and 4 GB of RAM for tens of cameras. For larger deployments, use 4 CPU cores and 8 GB of RAM.
  • 10 GB of free disk space for the image and system files, plus about 0.3 MB per retained snapshot. For example, 100 cameras checked hourly produce roughly 20 GB of snapshots per month.

At steady state the container uses about 1.2 GB of RAM. CPU usage is close to idle between check cycles and rises only while a batch of snapshots is being analyzed.

Network:

DirectionPort / DestinationPurpose
Inbound8080 (TCP)Web dashboard and API.
Inbound2022 (TCP)Built-in SFTP server that cameras upload snapshots to.
Outboundapi.platerecognizer.com on ports 80 and 443License activation and periodic license validation.
tip

If you are behind a firewall, whitelist the required IP addresses. Offline license activation is not available.