OpenCV - Yi Systems

Setup Development environment for ROS and OpenCV on Raspberry Pi


In my rover car project, ROS is the framework to communicate among all components, including motors, camera, user input and algorithms. OpenCV is the framework for image processing like lane detection and line following. ROS Indego is the TLS version, which is easy to install with Ubuntu 14.04. ROS Jade is easy to install, too. If you install Ubuntu 15 or later, then you need to build ROS from sources. This article shows how to install ROS Jade.

OpenCV and ROS: by a Raspberry Pi rover project


This is based on a rover project by using ROS as framework and OpenCV as image processing SDK. The rover runs by following a track which is detected from image sequences via Picamera. Hough transform and contour detection are the ways to get the track, then the direction of detected track is converted to rover direction. You can find the codes in my git repository.

Install Ubuntu on Raspberry Pi


This is to install Ubuntu 14.04 on Raspberry Pi, instead of Raspbian. With Ubuntu installed, it is much easier to install ROS from package repositories, or we need to build ROS from sources, which is a lot of work.

ROSCar - A rover test platform with Raspberry Pi, Ubuntu, ROS and OpenCV


This is yet another Raspberry Pi Rover project, which depends on camera as major visual input and uses ROS (Robot Operating System) as software framework. With ROS, I can concentrate on individual algorithm design, but not to worry about communication among all components. You can find my codes in github.

Yi ToolSets

There are four comprehensive tools included in Yi-ToolSet, please follow download link to try. Yi-ToolSet is a C++ SDK which serves several basic and advanced image processing needs, including:

  • Brightness, Contract, Exposure

    Highlight/Shadow recovery

    Tone Curve adjustment


    Color space conversion

    Local Details

    Local Contrast/Local Tone mapping

    Split tone

In this toolset, we utilize Qt to implement cross platform UI. OpenCV, OpenMP and Intel TBB are used to make parallel computing possible. We also implement our own memory management, such that it is ok to handle virtually any size of bitmap in resource limited environment (Android, iOS or embedde systems.)

They are available in source codes or SDK, on Windows, Linux, iOS and Android. These demo programs are currently available in Windows platform, will provide Linux/Android platform later.

Subscribe to this RSS feed

© Copyright 2007- Yi Systems, Inc. All rights reserved.

5009 Asteria St, Torrance, CA, 90503, U.S.A. | +1-310-561-7237 |