GithubHelp home page GithubHelp logo

online-stereo-calibration's Introduction

online-stereo-calibration

An online stereo calibration module for the iCub. This system calibrates the eyes of the iCub in an online manner and performs stereo reconstruction during active vision (version and vergence).

You can find more information about this algorithm in the paper:

  • "Markerless Online Stereo Calibration for a Humanoid Robot", Nuno Moutinho et al., 4th International Conference on Development and Learning and on Epigenetic Robotics, 2014

Environment

All the functionality was tested on machines configured with:

  • Ubuntu 12.04 LTS
  • YARP 2.3.63
  • OpenCV 2.4.9

Download and Setup

Open a terminal and navigate to the folder ($YOUR_FOLDER) where you want to download the package.

Now, run:

>> git clone https://github.com/vislab-tecnico-lisboa/online-stereo-calibration.git

In ($YOUR_FOLDER/online-stereo-calibration/conf) you have a config file stereocalib.ini where you can change the intrinsic parameters of your iCub cameras. You can also change the YARP ports names. The stereocalib_icubSIM.ini is already prepared to be used with the iCub Simulator.

Compilation

Go to ($YOUR_FOLDER/online-stereo-calibration) and do:

>> mkdir build
>> cd build
>> cmake ..
>> make

Running

At this point everything is set to successfuly run the module. Go to ($YOUR_FOLDER/online-stereo-calibration/build) and run:

>> ./onlineStereoCalibration

The system is ready and waiting for the YARP connections to be made. The system creates 3 input YARP ports, 3 output YARP ports and 1 input-output YARP rpc port (default names defined in the original config file):

Input port that receives the raw images from the left camera (before image rectification)

/online_stereo_calibration/image/left

Input port that receives the raw images from the right camera (before image rectification)

/online_stereo_calibration/image/right

Input port that receives the head encoders

/online_stereo_calibration/head_encoders/state

Output port that has the stereo rectified image from the left camera

/online_stereo_calibration/image/left/out

Output port that has the stereo rectified image from the right camera

/online_stereo_calibration/image/right/out

Output port that has the disparity image (in the left camera reference frame)

/online_stereo_calibration/image/disparity/out

Input-Output rpc port that receives an image point in the format [U V] taken from the rectified left image (online_stereo_calibration/image/left/out) and sends the 3D coordinates of that point in the format [X Y Z], represented in the left camera reference frame

/online_stereo_calibration/point_request/rpc 

The YARP connections should be made, in a different terminal, as follows (example using default YARP ports names defined in the original config file):

    • to start the online stereo calibration

    yarp connect /icub/cam/left /online_stereo_calibration/image/left yarp connect /icub/cam/right /online_stereo_calibration/image/right yarp connect /icub/head/state:o /online_stereo_calibration/head_encoders/state

    • to see the output rectified images and the disparity images

    yarpview /online_stereo_calibration/left/out/view & yarpview /online_stereo_calibration/right/out/view & yarpview /online_stereo_calibration/disparity/out/view & yarp connect /online_stereo_calibration/image/left/out /online_stereo_calibration/left/out/view & yarp connect /online_stereo_calibration/image/right/out /online_stereo_calibration/right/out/view & yarp connect /online_stereo_calibration/image/disparity/out /online_stereo_calibration/disparity/out/view &

    • to get the 3D coordinates of an image point from the rectified left image

    yarp rpc /online_stereo_calibration/point_request/rpc (example) 160 120 Response: -0.248432 0.289807 0.666966

Note: for the points 1) and 2) you can run the scripts located in ($YOUR_FOLDER/online-stereo-calibration/scripts), depending if you are using the real iCub or the iCub Simulator.

online-stereo-calibration's People

Contributors

nmoutinho avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.