Luxonis develops high-resolution cameras with depth vision and on-chip machine learning for real-time computer vision applications. Their technology enables users to implement advanced object detection and recognition capabilities in robotics and embedded systems, enhancing automation and perception in various environments.
Funding
$6.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Developing computer vision applications often requires integrating multiple cameras, sensors, and AI processing units, leading to complex and bulky setups. This complexity increases development time and cost, hindering the adoption of computer vision in robotics and embedded systems.
Solution
Luxonis offers a range of integrated camera systems with depth perception and on-chip machine learning capabilities, simplifying the development of real-time computer vision applications. Their OAK (OpenCV AI Kit) devices combine high-resolution cameras, stereo depth sensing, and powerful AI processing into a compact, easy-to-use package. This integration enables developers to quickly implement advanced features like object detection, semantic segmentation, and spatial AI without the need for extensive hardware and software configuration.
Target Audience
The primary audience includes robotics engineers, embedded systems developers, and AI researchers seeking to rapidly prototype and deploy computer vision solutions in various applications.
Features
- Integrated stereo depth sensing with up to 1 million points and a range of up to 25 meters
- On-chip AI processing for real-time object detection, semantic segmentation, and landmark recognition
- High-resolution 4K H.265 encoding at 30 FPS and depth sensing at 1MP and 120 FPS
- Support for standard and wide-angle lenses with up to 150° DFOV
- Object tracking for up to 20 objects with unique IDs
- Compatibility with popular AI frameworks such as Pytorch, TensorFlow, Keras, and OpenVINO
- Hardware and software are open source under the MIT license
- Options for USB or PoE connectivity