Plumerai demo on Arm/x86¶

This document provides usage instructions for the Plumerai Video Intelligence demo on Arm and x86 platforms. It includes a ready-to-run binary for evaluating the Plumerai products by running it live with a camera. The base documentation concerns running the people, vehicle, animal, and package detection demo. There is additional documentation for running the familiar face identification demo with automatic enrollment and with manual enrollment.

Please get in touch with our team to request the Plumerai Video Intelligence demo package if you haven't done so yet. Note that it is merely designed as a demo for evaluation purposes, and not for production usage. For production, we offer our Plumerai Video Intelligence library, which can be integrated into your application. You can find the API documentation here.

This demo uses the open-source GStreamer software to capture images from a camera and displays results on your screen. The GStreamer components are not optimized for speed in any way: the demo application might run significantly slower compared to actually using the Plumerai Video Intelligence library in a production environment.

The demo is pre-packaged for the following platforms: Linux x86-64, Linux aarch64, Linux armv7l, macOS x86-64, and macOS arm64. There is special support to run on a RaspberryPi with a PiCam camera. There is no Windows version available.

Apart from the GStreamer-based demo, we provide source code of a simple OpenCV webcam-to-display pipeline. This can be adjusted as needed for prototyping and can also serve as a demo. The documentation and source code is available in a public GitHub repository.

The next pages describe how to run the GStreamer-based Plumerai Video Intelligence demo:

• Installing and running the demo
• Troubleshooting
• Extra information for familiar face identification with automatic enrollment
• Extra information for familiar face identification with manual enrollment