OpenCV 3.0 / 3.1


OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library.

OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in commercial products. Being a BSD-licensed product, OpenCV makes it easy for businesses to utilize and modify the code. See


Reference Operating System for IoT includes the necessary libraries to run OpenCV applications.

For more information, code examples, and tutorials about using OpenCV, see

Python PIP Installation

Python Dependencies

For development of Python code using the Ref-OS-IoT, it is recommended to install the "pip" package management system in the module. Most uses require pip with python 2.7.

This is done from the device command line:

cd /usr/lib/python2.7

pip can then be used to install packages for example for pyserial:

python -m pip install pyserial

After updating PIP, install and import:

pip install opencv-python
>>>> import cv2

Python 3.x

If you want to use python version 3.x, run the command python3.; python 3 # opens python 3.5.2

You can default to the python3 by:

unlink /usr/bin/python
ln -s python3 /usr/bin/python

For information about enabling a webcam with Python, see USB Web Camera.

Para obter informações mais completas sobre otimizações do compilador, consulte nosso aviso de otimização.