ParkPow Plate Recognizer Snapshot GPU

Snapshot by ParkPow is a self-hosted license plate recognition service that reads license plates from vehicle images, using Nvidia GPU acceleration for fast…

  • AI
  • Media Applications
  • Other
  • Productivity
  • Tools & Utilities
Snapshot by ParkPow is a self-hosted license plate recognition service that reads license plates from vehicle images, using Nvidia GPU acceleration for fast on-premises processing.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

59/100 Fair

Maintained
72last commit 78 days ago
Popular
57672 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today, links checked 34 days ago

GitHub stars
672
Open issues
1
Last commit
2026-09-04
License
MIT
Activity
stale

Checked 13 days ago - source: GitHub (parkpow/deep-license-plate-recognition)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Requirements The GPU image requires an Nvidia GPU. You also need a Plate Recognizer API token or a running self-hosted Snapshot SDK. source

Fetched 38 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Do I need a cloud API key when running the self-hosted Snapshot SDK?

No, the example client can target a running self-hosted Snapshot SDK instead of the cloud API. The quickstart uses the local Snapshot SDK endpoint on port 8080.

Does the on-premise Snapshot GPU product require Internet access?

No, Plate Recognizer states that its on-premise software does not require Internet.

Can Snapshot data be sent to ParkPow?

Yes, Snapshot and Stream can forward LPR data to ParkPow. ParkPow can also integrate third-party data through its APIs.

Is an Nvidia GPU required for the Snapshot GPU package?

The vendor page states that no GPU is needed, noting that Stream can process 5-10 cameras on a mid-range CPU.

Can the example client restrict recognition to specific plate regions or process multiple files?

Yes, you can pass one or more --regions flags to limit recognition. It also accepts multiple image paths or a shell glob for bulk processing.

Answers sourced from github.com, platerecognizer.com, platerecognizer.com

Community

Collected 53 days ago - public community threads