JeVois smart machine vision camera

JeVois Smart Machine Vision Camera

Open-source quad-core camera effortlessly adds powerful machine vision

to all your PC, Arduino, and Raspberry Pi projects.

Get one!
Get one!

About JeVois

Open-source machine vision finally ready for prime-time in all your projects!

JeVois = video sensor + quad-core CPU + USB video + serial port, all in a tiny, self-contained package (28 cc or 1.7 cubic inches, 17 grams or 0.6 oz). Insert a microSD card loaded with the provided open-source computer vision algorithms (including OpenCV 3.4.2, TensorFlow, Caffe, Darknet, and many others), connect to your desktop, laptop, and/or Arduino, and give your projects the sense of sight immediately.

Intro video from our January 2017 Kickstarter

1,375 backers pledged $108,397 to help bring this project to life (216% funded).

Do you like buzzwords? JeVois is the world's smallest TensorFlow-enabled deep learning edge AI smart camera for IoT, computer vision, home automation and robotics!


Need powerful computer vision, artificial intelligence, and a deep learning camera for your project? JeVois runs deep neural networks that can recognize up to 1000 different types of objects, in under $50, 17 grams, 28 cc, and 3.5 Watts. Watch the video

Use Darknet-YOLO v3, MobileNet, MobileNet v2 + SSD, OpenCV Face Detection network, tiny-Darknet, and many other deep neural networks pre-packaged with JeVois, or train and deploy your own deep networks using Caffe, TensorFlow, Darknet or Torch.

Get one!

Getting started with JeVois

Get started on JeVois Start

Try the new JeVois Inventor (beta) graphical frontend for JeVois!

Windows   MacOs

Ubuntu 18.04   Ubuntu 16.04


and check out the instructions for JeVois Inventor to get started with programming new machine vision pipelines using full Python 3.6 + numpy + OpenCV 3.4 in minutes!

Want to discover what your new JeVois smart camera is capable of? Our guided tour will walk you through many of its available machine vision modules, from simple edge detection, to QR-code decoding, to detecting and recognizing objects in complex scenes.

Download Guided Tour               

  • Brief explanation of what each machine vision module does.
  • Example screenshots.
  • Sample images that you can show your JeVois camera.

Try it out with your kids!

Get started

Quick start, tutorials, downloads and resources

Get started quickly and download MicroSD images, developer kit Ubuntu packages, hardware-related files, and more at JeVois Start.

Find out more  Open Access

Intro doc

General introduction and core documentation

At the core of JeVois is a new C++17 machine vision framework combined with custom Linux kernel extensions, to simplify the tasks of grabbing images from a camera sensor and sreaming vision results to a PC over USB and/or to an Arduino over serial link.

Find out more  Open Source

Vision Modules

Bundled machine vision modules

The JeVois team has already developed a broad collection of computer vision modules that run directly on the smart camera's embedded quad-core processor. Modules are written in C++ or Python. From detection and decoding of QR-codes to object recognition to deep convolutional neural networks that can read handwritten digits.

Find out more  Open Source

Programmer Doc

Programmer documentation for vision modules

The 25+ machine vision modules bundled with JeVois provide great examples for how to write your own. Topics covered include using OpenCV and other computer vision libraries, using the onboard GPU and OpenGL-ES for real-time image filters, using NEON multimedia instructions, using multi-threaded processing, and more.

Find out more  Open Source


Community questions & answers

Ask questions and find answers about using and programming JeVois.

Find out more  Open Access

JeVois on GitHub