Ground-breaking AI for intelligent cameras. Proven on millions of devices, trusted by leading brands.
We are working on a future in which your doorbell tells you the kids got home safely. Your front door automatically opens while you carry the groceries. And the savannah warns the ranger of poachers. It’s a future that is safer and more thoughtful thanks to intelligent sensors inside all the things around us.
We bring accurate
Tiny AI to the edge.
Combine it with powerful Vision
Language Models in the cloud.
Empowering cameras to see, understand, and respond.
A large number of intelligent chips are required to make computing ambient. Therefore, they have to be small, cheap, and low-power. Our technology works on $1 chips with 1MB of memory. These are so efficient, they can be powered by a coin battery or small solar cell.
Plumerai’s powerful Vision Language Models run in the cloud, guided by the Tiny AI on the cameras. The edge AI provides context and selectively activates our Vision Language Model only for moments that need deeper analysis. The result: rich scene understanding with features like AI Captions, at a fraction of the cost of cloud AI services.
Plumerai has developed a complete software solution that includes Familiar Face Identification, Stranger Identification, People, Vehicle, Animal and Package Detection, Advanced Motion Detection, AI Video Search, to find any moment in your camera history with a natural-language query, and AI Captions, that describes video clips in plain English. The AI software is deployed on all major camera SOC and cloud platforms and on millions of cameras in the field. To ensure safe and responsible deployment in the US, EU, and UK, the software is compliant with local privacy laws, including GDPR, CCPA, BIPA, and the EU AI Act.
Traditional smart home cameras generate many unnecessary alerts triggered by moving objects or changes in lighting. Plumerai's AI solution eliminates these false alarms, ensuring users receive only relevant messages. Tag known safe individuals, such as the weekly gardener, to avoid unnecessary notifications. Precise messages like "Stranger on the driveway" or "Rachel came home" keep users informed and engaged. This encourages continued use of the app, enhances the overall experience, and provides peace of mind.
We combine our model architectures, inference engine, datasets, and Vision Language Models into a turnkey Video Intelligence pipeline. The same vertical integration delivers highly accurate AI from tiny edge chips to the cloud.
Plumerai brings AI features like Familiar Face Identification, Multi-Camera Re-Identification, AI Video Search, and AI Captions together in one Video Intelligence pipeline. Behind each feature, multiple AI models work in concert, with the complete pipeline optimized end to end for efficiency across camera and cloud. The AI can run on cameras, on local servers, or in the cloud, giving customers flexibility of deployment.
We develop our neural networks from scratch. We optimize for small embedded devices with customized model architectures and training strategies, based on our world-class research on model quantization. This results in tiny but highly accurate AI models, enabling even Vision Language Models to run in the camera.
Our Vision Language Models run in the cloud and are activated selectively by the on-device pipeline, only for the moments worth deeper analysis. This delivers richer scene understanding for features like AI Video Search and AI Captions, without the cost of running a Vision Language Model on every frame.
We collect, label and build our own dataset of over 100M images and videos. Our data pipeline identifies failure cases to ensure that our models are highly reliable and accurate. We hire data actors that go out in the field to capture additional data. This approach guarantees the diversity and relevance of our training data, and ensures an ethical data collection practice.
The Plumerai Inference Engine makes AI models run efficiently on CPUs, with minimal compute and memory. It is optimized for Arm Cortex-M, Arm Cortex-A, and RISC-V processors.
We work closely with semiconductor companies that offer high performance and low power microcontrollers and SOCs. Using these chips, our software powers security cameras, consumer electronics, smart home cameras, and intelligent sensors. Our larger models run efficiently in the cloud and can be self-hosted in customer environments.
Thank you for submitting the form. We’ll get in touch as soon as possible.
There was an error submitting the form. Please try again later.
We’re partnering with industry experts
