FRC 2168 OpenCV library for the roboRIO and BeagleBone processors

OpenCV is the premier open source vision library and can be found in many commercial and research robots. From the OpenCV web site:

“OpenCV is released under a BSD license and hence it’s free for both academic and commercial use. It has C++, C, Python and Java interfaces and supports Windows, Linux, Mac OS, iOS and Android. OpenCV was designed for computational efficiency and with a strong focus on real-time applications. Written in optimized C/C++, the library can take advantage of multi-core processing. Enabled with OpenCL, it can take advantage of the hardware acceleration of the underlying heterogeneous compute platform. Adopted all around the world, OpenCV has more than 47 thousand people of user community and estimated number of downloads exceeding 9 million. Usage ranges from interactive art, to mines inspection, stitching maps on the web or through advanced robotics.”

FRC Team 2168 has done a build of OpenCV that is customized for the FRC competition robots that they are graciously contributing to the FIRST community. It includes support for the Microsoft USB camera and is built to run on an ARM processor, think roboRIO and BeagleBone computers. It also has been run on the Tegra TK1. They have also included an example vision application written in C++ which uses OpenCV to perform last years vision task of detecting a hot goal. The example itself is very simple using only basic filters in OpenCV, (but it is exactly what we used throughout the 2014 competition season).  The example can be run directly on the RoboRio or a number of other Armv7 based processors such as the beaglebone family. The example supports processing images from a USB Camera, IP Axis Camera, or from a file. I have modified the program to select command line arguments which will allow it to capture images from a IP axis camera, webcam, or a file. I’m sure that they will continue to improve the library and provide some level of support for teams that are using it.

You can find additional information on this ChiefDelphi post and on their GitHub site.