Introduction

What is OpenCV?

OpenCV (Free Open Source Computer Vision) is a library of programming functions mainly aimed at real time computer vision. It has a BSD license (free for commercial or research use). OpenCV was originally written in C but now has a full C++ interface and all new development is in C++. There is also a full Python interface to the library.

Example applications of the OpenCV library are Human-Computer Interaction (HCI); Object Identification, Segmentation and Recognition; Face Recognition; Gesture Recognition; Motion Tracking, Ego Motion, Motion Understanding; Structure From Motion (SFM); Stereo and Multi-Camera Calibration and Depth Computation; Mobile Robotics.

Learning OpenCV

• 

• Learning OpenCV: Computer Vision with the OpenCV Library

  • by Gary Bradski and Adrian Kaehler, O'Reilly Press, October, 2008.

• Japanese Translation: 詳解 OpenCV (単行本（ソフトカバー）)

• Chinese Translation: 学习OpenCV（中文版）(预订中,估价) [新品]

• It is a textbook that covers

  • Computer vision in general, intuition to the algorithms and theory
  • User's guide to OpenCV with pragmatic working examples
  • Function specs and tuning intuitions

OpenCV 2 Computer Vision Application Programming Cookbook

• Cookbook application examples, OpenCV 2.

• 

Contributors

• OpenCV Logo

Announcements

• OpenCV is in Google Summer of Code Project page.

• OpenCV now has a new developer site: http://code.opencv.org. A new user site is in progress.

• The current release version is 2.3.1 (August 2011)

  • But: OpenCV 2.4 Beta SVN branch is out (April 16, 2012), see Change log. 2.4 is due end of April 2012.

Nightly builds of the documentation and (new) tutorial section are available at http://opencv.itseez.com

• Weekly developer meeting notes, latest meeting at bottom.

  • OpenCV library updates on Twitter

  • Android-OpenCV updates on Twitter

• Change log (what changed in the official releases)

• User Group

How do I Download OpenCV?

• Download the current release of OpenCV for Windows, Unix, Linux or Mac or Android.

• To get the latest SVN code, use: svn co https://code.ros.org/svn/opencv/trunk/opencv To build, see the Install Guide.

  • To see the latest SVN revision, run: svn info https://code.ros.org/svn/opencv/trunk/opencv

• Next OpenCV Official Release: 2.4 end of April 2012

Release Numbering Philosophy:

• The convention OpenCV follows for release numbering is:

• We will try to loosely follow Linux minor number even-odd release conventions where the API for new functionality is less stable/documented on odd minor numbers and more stable/documented on the even numbers.

Installing OpenCV

• Follow the Install Guide to install the current release for Windows, MacOSX, Linux, Android or iOS.

Getting Started with OpenCV

1. Using Visual C++ and OpenCV

2. Using Eclipse IDE and OpenCV

3. Using C++ Builder IDE and OpenCV

4. Using DevCpp IDE and OpenCV

5. C/C++ interpreter Ch and OpenCV.

6. How do I compile OpenCV and OpenCV programs in Linux? - Also see notes in the Linux section of OS Specific Stuff below

7. Using OpenCV with Visual C++ and Microsoft's DirectShow

8. How do I compile OpenCV and OpenCV programs on Mac OS/X?

Frequently Asked Questions

Problem Specific Frequently Asked Questions

1. Beginners/Newbie FAQ's (how to access a pixel etc.)

2. Is there a user group or forum for OpenCV? Yes: OpenCV Yahoo Group

3. How to use OpenCV to capture and display images from a camera

4. Which video file formats can I use with OpenCV?

5. How do I use OpenCV to Detect Faces?

6. Using OpenCV for Face Recognition

7. How to use OpenCV to Detect Objects?

8. How to use the OpenCV Blob Extraction Library

9. How do I correctly refresh my HighGUI application?

10. Where to download DirectShow?

11. How to Display more than one image in a single window?

12. CodingStyleGuide

13. VideoSurveillance

14. Where do I report a bug or request new features or raise documentation issues?

    • In general, you can go to https://code.ros.org/trac/opencv/wiki/

      • You will first need to register at https://code.ros.org/gf/ (This is only for spam control, your name is not given out). Then:

      • Click on "new ticket" to file a new bug report or feature request, or submit a patch.
      • Click on "view tickets" or "search" to look for existing tickets - probably your problem is already known or even fixed in the latest SVN version.

    • Bug Notes:

      • Do the work: Submit as much information as you can (what OS, what compiler, what OpenCV version).
      • To help rapidly fix the bug, it is preferable to also attach a short program plus data that reproduces the problem.
      • You can and should submit bugs for documentation. Again, be specific (C, C++, Python). What exactly was missing, confusing or wrong.
        • If you know how the documentation should be fixed, submit that too.

15. Help! I can't get my code to compile!

Tutorials

1. OpenCV_Talks

2. OpenCV Tutorial and Cookbook

3. POSIT tutorial (3D Pose Estimation using OpenCV and OpenGL)

4. Kinect camera page (Using the XBox Kinect depth camera with OpenCV)

5. A short introduction to programming with OpenCV

6. Tutorial on how to use Philips webcam features with OpenCV on Linux

7. Introduction to OpenCV (in Turkish) 1 2 3 4 5

8. Introduction to programming with OpenCV and IPP - (2003)

9. Sample program for Face Recognition

10. SamplesPrograms

11. Small Example Programs 1 2 generated by cvPreProcessor

12. DCTmod2 Feature For Face recognition

13. How to significantly speed up the cvMatchTemplate() function

14. Примеры (>10) использования OpenCV + С++Builder6 + перевод части документации, форум

15. Instalasi OpenCV di Borland C++ Builder 6 -- Tutorial Bahasa Indonesia

16. ICRA 2009

17. CVPR 2010

18. A short guide to getting started with OpenCV

19. OpenCV Tutorials and Source code (includes Face Recognition & Shirt Color Detection).

20. ECCV 2010 (Computer Vision and 3D Perception for Robotics) OpenCV Slides (first talk)

21. OpenCV шаг за шагом - OpenCV step by step

22. OpenCV: Some generic foils to include in other talks

23. Vision Systems in Robotics_ICVS_.pdf Keynote to ICVS 2011 includes detailed programming appendix.

24. OpenCV Quick Guide - A free book about OpenCV library

Workshops/Discussions

1. ARSO 2011 Improving Robotic Perception

Full

Support, Documentation & Resources

Technical Support

There is no formal technical support for OpenCV, but there is a very active OpenCV Forum at Yahoo Groups where you are welcome to post your questions. A mirror of the group archive can be found at Gmane.

Bug Report Page

• Submit bugs: Report a bug or request new features or raise documentation issues on our bug tracking page.

  • You will first need to register at https://code.ros.org/gf/ (This is only for spam control, your name is not given out). Then:

  • Click on "new ticket" to file a new bug report or feature request, or submit a patch.
  • Click on "view tickets" or "search" to look for existing tickets - probably your problem is already known or even fixed in the latest SVN version.

• Bug Notes:

  • Do the work: Submit as much information as you can (what OS, what compiler, what OpenCV version).
  • To help rapidly fix the bug, it is preferable to also attach a short program plus data that reproduces the problem.
  • You can and should submit bugs for documentation. Again, be specific (C, C++, Python). What exactly was missing, confusing or wrong.
    • If you know how the documentation should be fixed, submit that too.

Documentation of Functions

• C++

• C

• Python Docs

Other:

• cvBlobsLib

• External OpenCV 1.0 API with function search on cs.indiana.edu

• External OpenCV 2.0 API with function search on fscience.net

OpenCV Online Resources

• The Official Home Page

• The OpenCV China (OpenCV中文站)

• To get the latest SVN code, use: svn co https://code.ros.org/svn/opencv/trunk/opencv

  • To build, see the Install Guide.

  • We used to use sourceforge where you can still get the released versions from. SourceForge

    • main page: http://sourceforge.net/projects/opencvlibrary

    • Note: the bug and patch trackers on sourceforge are not used anymore. Use https://code.ros.org/trac/opencv instead.

• The OpenCV Forum at Yahoo Groups

• The #opencv IRC channel on Freenode -- currently 'Un-official'

• OpenCVDotNet - OpenCV wrappers for .NET Framework.

• SoftIntegration - OpenCV wrappers for Ch.

• OpenCV Naver Community Forum (Korean)

• EffortFor3dReconstruction - Community document to bring forward 3D reconstruction in OpenCV

• Emgu CV A cross platform .Net wrapper for OpenCV

• OpenCvSharp A cross platform .Net wrapper for OpenCV 1.1, written in C#. All CxCore, CvReference, MachineLearning functions wrapped. Documentation of functions included in XML Format

• opencv.jp (Reference manuals and sample codes in Japanese)

• JavaCV - Contains Java wrapper classes for the full C/C++ API of OpenCV 2.4.x, also works with Android, MATLAB, Scala, applets, etc.

• Drexel Uni tutorials - Noah Kuntz's tutorials for beginners to learn how to use OpenCV.

• AI Shack - Tutorials/articles on OpenCV, computer vision in general and robotics.

• Shervinemami.co.cc - Tutorials for OpenCV such as Face Recognition and Colored Blob Detection.

Ideas for the Future of OpenCV

• * Our SummerOfCode page describes project ideas for the Google Summer of Code. The SummerOfCodeApplication page shows current status of our application to the program.

• Mac_OS_X_OpenCV_Port holds specific ideas for OpenCV on Mac OS X

OS Specific Stuff

Linux Version

• In beta 5, test programs are not built by default. To build, run "make check" (see CxTest for more information on running and writing tests).

• The current distribution of OpenCV (0.9.7 beta 5) does *NOT* work with GCC 4.0 or 4.1. Before compiling, you will have to run the configure script as follows: CXXFLAGS=-fno-strict-aliasing ./configure . GCC 4.0 will *NOT* (but 4.1 will) give *ANY* warning whatsoever that something is wrong (it is a bug of GCC 4.0), but it will *NOT* work, so you have been warned. If this option is not used with GCC 4.0 or 4.1, the resulting library has lots of errors as evidenced by failed tests in the test programs and the test programs segfaulting. Alternatively, you can also use the CVS version. The aliasing bugs are fixed in the CVS version.

• Building will fail on x86_64 platforms and GCC 4.0.2 using the beta 5 release with errors about various SSE things like "'__m128d' was not declared" . Since GCC 4 and beta 5 are broken anyway, use the CVS version. GCC 3.2.3 may also work.

• Sometimes the configure script may generate a bad makefile for your system if it was generated by a version of autoconf/automake/etc that is too old for your system. For example, you may get linking errors for the library files on x86_64. To fix this, run autoreconf in the root opencv directory (where configure is) to regenerate the scripts. Then run make distclean and run the newly generated configure to generate new makefiles.

• Compiling OpenCV and OpenCV programs on Linux

Linux OpenCV Camera Compatibility

• For some cameras (e.g. Quickcam Express) try running "v4lctl -c /dev/video0 setinput X" to get a valid list of inputs and then set it appropriately with the same command.

(*) If you have problems with synchronization while using cvQueryFrame using PS3Eye please contact me: there's a workaround

MacOS X Version

OpenCV 2.0 for Mac/Linux/Unix is available on the files section of SourceForge.

Until the next release of OpenCV, there is now a pre-built version (universal binary Private Framework, together with a demo application). Have a look at the PrivateFramework page or download it from http://www.ient.rwth-aachen.de/cms/software/opencv/.

Additional information on building and on the current state of development can be found on the Mac_OS_X_OpenCV_Port page.

MacOS X Compatible Cameras

Windows Version

Windows Compatible Cameras

DirectShow without the hassle

You can use the video input library at http://muonics.net/school/spring05/videoInput/ to avoid the messiness of dealing with DirectShow. It even works for direct capture to the imageData field of an IPL image, though I found that the result was upsidedown and had red and blue switched. (Note from author of videoInput: new version out! With option to have RGB or BGR pixels and loads of other features)

Firewire 1394 cameras without Direct X

You can install the CMU 1394 driver for your camera and then use the API of this driver to capture video from the camera. In this way, you can avoid the use of DirectX. See example for details.

VC Smart Cameras

OpenCV can run on VC Smart Cameras now. Vision Components + OpenCV

Leutron Vision PicSight Smart GigE cameras

OpenCV runs on PicSight Smart GigE Cameras. PicSight Smart GigE & OpenCV

Development

This page is to describe serious development aimed at inclusion or expansion of OpenCV.

Development

• The ongoing project management page for the core development team can be found at OpenCV Development at Willow Garage

• OpenCV on Twitter

Roadmap

• October 2010 OpenCV Release 2.2

Past plans

• Summer 2009

  • Ideas that one could work on OpenCV Ideas 2009

• 2008

  • The feature list and plan for the next major release of OpenCV is here: OpenCV 2009/08

People

Feel free to add yourself here... BUT NO spam or non-vision related links

• Add Vision companies and vision services in the http://opencv.willowgarage.com/wiki/Welcome/VisionCompanies page below.

• Deepak Nayak - Freelance Researcher/Developer - AutoSegment - Fully automated moving object detection using pre-stored images

• Steven Hickson Clemson University, C++/C# OpenCV and FPGA projects with javascript and HTML 5.0

• Emrah Basaran-Erciyes University/Turkey [ emrahbsrn@gmail.com ]

• Gecko Geek (FRENCH Tutorials, like Color Tracking)

• - TerryMay-USA

• Alex Karpus - Ottawa, Canada - ported OpenCV 2.0 (cv, cxcore, highgui) to WinCE SDK v6.0 (Project Details, Downloads)

• Gennady Gilin [ genady.job@gmail.com ] -

• Riza Alaudin Syah SharedSystem Inc. Japan

• Alex Hunt email

• Randy Cahya Wihandika [ rendicahya@yahoo.com ] - Electronic Engineering Polytechnic Institute of Surabaya - Indonesia

• Danang Suharno - Ngadinegaran, Yogyakarta, Indonesia

• Fayas A [ fayas.a@gmail.com ]- Phd student

• Pratap Vardhan-Computer Vision & Image processing enthusiast, India http://pratapvardhan.blogspot.com/ [ pratapapvr@gmail.com ]

• Chris Harris- PHP expert.

• Tomasz Kolinko, using OpenCV for AR and marketing games purposes, Mechanekin, Warsaw, Poland

• Gary Bradski 266

• Adrian Kaehler

• ChristophSeibert

• Stephen Antony

• OlivierBornet

• MarkAsbach - working on Mac OS X port, Framework, Python

• Parameswaran

• RalfStauder

• RicardBorras

• PankajVallabh

• MohammadHeydari mdh.heydari@gmail.com

• JavierBarandiaran

• JairoSanchez

• AndresCaro

• XiaomingLiu

• DominiqueBelhachemi

• Michael T. Matibag, michaelmatibag@gmail.com , micmat_aztecx@yahoo.com

• Kecsap

• Luiz Reginaldo

• Shiqi Yu

• BarisEvrimDemiroz

• ASBG Group in Portugal

• Francisco Bernardo

• Haar Hand Tracker Losi, losteiner@gmail.com

• RomanStanchak

  • Sebastian Montabone - Fine Grained Saliency

• Le Khanh Thanh,Ha Noi, Viet Nam. comp_vis@yahoo.com

• Lismont Kevin, stvv@pandora.be , Belgium

• Thijs Triemstra

• Zhaoxiang Zhang

• ChrisFairles

• Sami Bourgou

• Shirish Goyal

• MoaathALRajab

• Laurent Wagneur, France, INGENICA http://www.ingenica.fr

• mailto:congthienvn@yahoo.com Pham Cong Thien, Suwon, Korea http://www.hcmuaf.edu.vn/cackhoa/kcntt/nhanvien/pcthien/index.html

• OpenCV integration for Prosilica cameras and VC Smart Cameras Antonio Yu, Metron Hong Kong Ltd. http://www.metronhk.com

• Jérôme Landré, France - http://pagesperso-orange.fr/jerome.landre/index_en.xhtml

• Lee Seongjoo, Republic of Korea Artificial Intellegence Laboratory, Yonsei University

• Son Do-Lenh

• NicolasSaunier

• TamasUngi - and his tutorial notes

• Phan Anh Vu - Hanoi University of Technology - virces931511@yahoo.com - http://cntt.tv

• Oscar Deniz Suarez, Spain http://mozart.dis.ulpgc.es/Gias/oscar.html

• Bluekid

• João Quintas, Portugal - vazamentos

• Sunu Wibirama - OpenCV Indonesia

• Cristoffer Lee

• Matthew Bennett - Course Leader of BTEC Games Design at Gloucester College and author of http://colourisation.pbworks.com

• BENABBAS Yassine - OpenCV Tutorials(google knols)- PhD Student at Lille1

• Naotoshi Seo - Tutorial - OpenCV haartraining OpenCVX - Yet another OpenCV eXtension functions

• Nash - OpenCV Tutorials

• Alasdair Swenson - VJ pop-eye alasdairswenson@gmail.com

• A. Rahman Rezazadeh - Denmark abr@agrotech.dk Agrotech

• Vizmatic - Computer vision software development

• Roberto Robot umanoide MecWilly - Italy

• Matia Pizzoli Sapienza Università di Roma - Italy

• Andrea Carbone Sapienza Università di Roma ALCOR Lab - Italy

• Jacopo Parvizi -Student at DIIGA - Università Politecnica delle Marche, Italy

• Burak Çayır - Galatasaray University, Istanbul-TURKEY - burakcayir@gmail.com - http://www.gsu.edu.tr

• Kazım Hanbay - Bingol University,Bingol - TURKEY - kazimhanbay@yahoo.com - http://www.bingol.edu.tr

• Stephen S. Nestinger - University of California, Davis - USA - ssnestinger@ucdavis.edu

• Daniel Cervantes

• WeiYan Ph.D. student- University of Illinois - USA - weiyan2@illinois.edu

• Calderon Francisco - calderonf@gmail.com - Universidad Javeriana Bogotá - documentación en español.

• Quang Nguyen - quangndba@gmail.com - Fix8.com - [Mobinex Inc.]

• Martin Dale - Automotive Development.

• Flavio Bernardotti - Computer Vision Encyclopaedic Forum with 30.000 documents, projects with source, opencv papers ...

• A.Rahman Rezazadeh abr@agrotech.dk

• JeanReneBedard jrbedard@gmail.com

• Claudio Concilio Robotics claudio.concilio@TSKILLS.com - Italy

• Juno Seo http://www.nml.t.u-tokyo.ac.jp/~jhseo Visual Servoing nic.seo@gmail.com - Korea

• Dr.Srinivas Ganapathyraju - Professor - Canada - Interested in OPENCV applications to robotics- Email: world_hiker@yahoo.com

• JIA Pei http://www.visionopen.com Active Appearance Model - UK

• Fatih Ömrüuzun - Middle East Technical University, Ankara - TURKEY f.omruuzun@gmail.com http://fscience.net

• Calven Eggert - Toronto, Canada - iPhone Development

• Yannick Verdie - Virginia Tech, USA - working on Mac OS X port, Framework. Vislab website ...

• DI Andreas Heindl - Phd Student - working on automated cell detection in various tissues Andreas Heindl

• Vijay C Narayan - Robot Enthusiast - Working on Robot vision and navigation Vijay C Narayan

• José Alonso Ybanez Zepeda - Computer Vision Research at Ayotle -Email: jaybanez[AT]gmail.com

• Nicole Hogan

• Vijay Daniel, rLambda, Chennai, India - Working on Android port

• Cem Arslan, Istanbul-Turkey, CodeGear 2009 Project, cemarslan@mac.com

• Wang Kang - Nanjing University of Infomation Science and Techlonogy My Tech Blog novertina@aol.com

• Walter "Myzhar" Lucetti - Computer/Robotic Engineer Home Rover Project email

• Samuel Audet - Author of JavaCV

• Burak Ofluoglu - HP-ITU Software Innovation Center Burak Ofluoglu

• Fatih Taspinar-The University of Kocaeli, Turkey - realtime object recognition, fatihtsp@gmail.com

• Sebastian Müller - study project: realtime ocr for math formulas with webcam (named blackbird) install and working with opencv/webcam on linux, wiki in german language

• Diego Schmaedech - Brazil - Working on Eyetracking System

• Ryan Lei - CMLab, NTU, Taiwan - Working on Object Recognition, and Mac OS X Wiki pages here.

• Calven Eggert

• Wang Wei Da - yester-place- wa114040@gmail.com

• Gonzalez, Jesus - Using OpenCV and uEye Cameras for Aerial Servoing Control. University of Seville- Spain - susogv[at]gmail.com
• Anirudh Sharma -touchaddict - using OpenCV for tabletop interactions - anirudhsharma dot crypto at gmail dot com

• Thomas Bhatia

• Gianfranco S. del Mundo; Mapua Institute of Technology, Philippines; BSIT Student, Image processing to develop a Remote Eye Gaze Tracking System.

• Jai Pillai - Vision Researcher, University of Maryland - Object tracking, Adaptive smoothing code available at http://www.umiacs.umd.edu/~jsp/Downloads.html

• Shervin Emami - Australia - Robotics, Mobile Computer Vision at NVIDIA. OpenCV tutorials & code

• Alex Barry - Kitchener, Ontario, Canada - Open source implementation for eye tracking using cheap hardware. Code Repository - Home Page

• Alex K. Seewald - Seewald Solutions Austria, Europe. Using OpenCV for many projects, including eye tracking using off-the-shelf USB webcams and real-time deflickering of high-speed video. Some demo videos on Youtube, many more projects on research homepage.

• David J Barnes - Cognitive Vision systems for Robotics, Chicago, IL

• Phuc Tran - RMIT Vietnam graduated - phuctran0302@gmail.com

• Carlos Aravena C. -- Universidad de Chile -- Face Recognition, image processing, http://hayabusa.die.uchile.cl/

• Bruno Nascimento - Observit, Lda. - Portugal, Lisboa - Video Analytics. Software Engineer. bnascimento[at]observit.pt

• Andrew Leifer - Harvard University, PhD student, biophysics. Real-time image processing for optogenetics, code

• K.A.Mamun; Dublin City University,Ireland; PhD student, Image processing to develop a Surveillance and patient monitoring module for a Hospital Robit.

• Taiya Carleton - Wild Rhombus Software, Toronto, Canada - Artist and Software Engineer, using Optical Flow for movement tracking

• Robert Jobbagy - Hungary - Image Processing, Medical Image Processing and Video Surveillance,wxOpencv and gst-opencv developer

• Rahul Kavi - - US - Researcher/Developer Computer Vision, Computer Networks.

Vision Companies

• This section is for computer vision companies that offer vision services or who use OpenCV.

Companies Offering Computer Vision Services:

• VisionBlaster - Offers computer vision consulting, and game engine integration (Unity3d, Ogre, Quest3d, etc)

• Itseez West, Main contributor to OpenCV, computer vision consulting.

  • Also uses OpenCV in products.

• Vizmatic, Computer vision software development

• Applied Minds -- High end research spanning bio to robots to vision to building design

  • Also uses OpenCV extensively

Companies Using OpenCV:

• Willow Garage, for robotics, object recognition, navigation

• VideoSurf, Video surfing, video summary, video search

• Google, (reputably) Streetview, Maps, Bookscan, YouTube, Picassa ...

• Poseidon Computer vision based drowning prevention system.

• Zeitera -- Content Identification and Video Analytics

• Seven Solutions -- Video Analytics and Surveillance based on OpenCV

• Amscient -- Computer Vision, Imagery and Video Analytics

• Orpix -- A computer vision technology company that offers domain specific solutions such as vehicle make and model recognition and logo recognition. Makes extensive use of OpenCV.

Quick Links : FAQ - UserGroup - Download - Bugs. Docs: C++, C, Python, Index