# ParkPow USDOT Recognizer Snapshot

ParkPow USDOT Recognizer Snapshot is a self-hosted ai app. A ParkPow-powered self-hosted tool that reads United States Department of Transportation (USDOT) numbers from vehicle pictures. It is open source and self-hosted, installable on Docker Hub and Unraid.

Canonical page: https://ourlocalhost.com/app/2402/parkpow-usdot-recognizer-snapshot

## Description

A ParkPow-powered self-hosted tool that reads United States Department of Transportation (USDOT) numbers from vehicle pictures.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

59/100 (Fair), based on 3 of 4 factors.
- Maintained: 72 (last commit 78 days ago)
- Popular: 57 (672 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)

## Links

- Docker Hub: https://hub.docker.com/r/platerecognizer/usdot
- Official website: https://platerecognizer.com/
- Unraid: https://ca.unraid.net/apps/parkpow-usdot-recognizer-snapshot-1oghwie142a1v6?q=ParkPow-USDOT-Recognizer---Snapshot
- GitHub: https://github.com/parkpow/deep-license-plate-recognition

## Common questions

### How do I install this app on an Unraid server?

Use Community Apps on the Unraid OS server and install ParkPow-USDOT-Recognizer---Snapshot from the Unraid app page.

### Do I need a GPU for Snapshot inference?

No. Snapshot inference is 50-100 ms, Stream processes 5-10 cameras on a mid-range CPU, and no GPU is needed.

### Can I run the recognition without an Internet connection?

Yes. Plate Recognizer offers on-premise software that can run without Internet, in addition to cloud deployment.

### Can I send camera LPR detections to ParkPow?

Yes. ParkPow can forward LPR data from a variety of cameras, including Snapshot and Stream, to the Premium Dashboard.

---
Source: Our Local Host (https://ourlocalhost.com/app/2402/parkpow-usdot-recognizer-snapshot), the self-hosted and open-source app directory.
