Object detection with Xnor's AI on the Edge

LEARN MORE

From the Creators of YOLO: Xnor’s object detection technology

Get state-of-the-art efficiency and accuracy while minimizing CPU and memory utilization. Our machine learning models can run in real time in any environment; from low-cost 1 GHz ARM processors running on an embedded device, to cloud-hosted servers & GPUs.

Powerful. Precise. Efficient.

Xnor’s object detection models stand at the head of the pack

Multi-Object Detection

Recognize dozens of objects in a single image or in a live video stream - without compromising efficiency or accuracy.

Hundreds of Objects

Recognize hundreds of objects from dozens of categories like people, animals or household items, while utilizing minimal onboard memory.

Tracking

Track people or animals as they move through different rooms and buildings, passing through the field of view of different cameras.

Xnor’s Object Detection technology in action

Our object detection models run efficiently on embedded hardware to make smart refrigerators a reality.

Our object detection models for people, pets and vehicles and our face identification models are powering a new era of smart homes.

Contact Xnor to learn more about how you can incorporate the next generation of AI into your products

The Xnor Advantage

Accuracy

Run highly-accurate AI tasks in real-time, without the need for cloud-based resources.

Speed

Perform complex AI tasks 10x faster than AI solutions that require a GPU or neural accelerator.

Security

Algorithms live and run on-device, so data doesn’t need to be sent in or out to a third party.

Energy

Xnor’s AI models are up to 30x more energy efficient than other solutions.

Memory

Xnor’s models are so small that they require 15x less on-board memory than other solutions.

Hardware

Run deep learning on commodity CPUs all the way up to cloud-based GPUs with our hardware agnostic solutions.