Plumerai Documentation Overview¶
These pages contain technical documentation for Plumerai’s products. For information about the company, visit our main website or our blog for updates and news.
This overview page provides links to the most important documentation sections, which are also accessible via the sidebar on the left.
Plumerai Video Intelligence¶
Plumerai Video Intelligence is a complete on-device AI stack for cameras and video doorbells, deployed and tested on millions of devices in the field. It provides fast, accurate detection of people, vehicles, packages, animals, and supports advanced features like Familiar Face Identification with Stranger Detection and even Vision Language Model (VLM)-based features that can run on device. The models are highly optimized for low-power hardware and can be integrated using a unified API.
The following 'Plumerai Video Intelligence' components are available:
- Object Detection includes:
- Plumerai People Detection
- Plumerai Vehicle Detection
- Plumerai Animal Detection
- Plumerai Package Detection
- Plumerai Familiar Face Identification (FFID)
- Plumerai Stranger Detection
- Plumerai Advanced Motion Detection
- Products based on Vision Language Models ('VLM'):
The Plumerai Video Intelligence software runs on a wide variety of platforms and operating systems, while using the same unified API everywhere. Depending on the platform used, products based on Vision Language Models might require running one or more components on a mobile device, hub, or in the cloud.
We also provide demo applications that run on Arm Cortex-A and x86 CPUs, on an ESP32-S3 microcontroller, or directly in your browser.
Plumerai Inference Engine¶
We've also built the world’s fastest deep learning inference engine for Arm Cortex-M and other microcontrollers. You can find out more about the inference engine on our blog or try it out with your own model.
The technical documentation can be found here.