Community Core Vision, CCV for short (aka tbeta), is a open source/cross-platform solution for computer vision and machine sensing. It takes an video input stream and outputs tracking data (e.g. coordinates and blob size) and events (e.g. finger down, moved and released) that are used in building multi-touch applications. CCV can interface with various web cameras and video devices as well as connect to various TUIO/OSC/XML enabled applications and supports many multi-touch lighting techniques including: FTIR, DI, DSI, and LLP with expansion planned for the future vision applications (custom modules/filters).

This project is developed and maintained by the NUI Group Community, We encourage you to get involved.


  • Simple GUI - The new interface is more intuitive and easier to understand and use.
  • Filters (dynamic background subtraction, high-pass, amplify/scaler, threshold) - This means it will work with all optical setups (FTIR, DI, LLP, DSI). More filters can be added as modules.
  • Camera Switcher - Have more than one camera on your computer? Now you can press a button and switch to the next camera on your computer without having to exit the application.
  • Input Switcher- Want to use test videos instead of a live camera? Go ahead, press a button and it will switch to video input.
  • Dynamic Mesh Calibration - For people with small or large tables, now you can add calibration points (for large displays) or create less points (smaller displays) while maintaining the same speed and performance.
  • Image Reflection- Now you can flip the camera vertical or horizontal if it is the wrong way.
  • Network Broadcasting - You can send OSC TUIO messages directly from the configapp for quick testing.
  • Camera and application FPS details viewer - Now you can see the framerate of both the tracker and camera that you are getting.
  • GPU Mode - Utilize your GPU engine for accelerated tracking.
  • Cross-platform - This works on windows, mac, and linux.
Upcoming Milestones:
  • ROI Selection- Optimizing processing by using only the Region of Interest.
  • Optical Flow - Gives you momentum variables out of the video stream.
  • Object/Pattern Tracking - Tracks fidicuals and objects places on surface.
  • Multiple Camera Support - Camera stitching and calibration for larger environments.


Getting Started - Quick Guide

  1. Download and extract the latest build of CCV.
  2. Launch the CCV application (.app, .exe, etc).
  3. Adjust the filter sliders to suite your sensing technique.
  4. Enter calibration mode and test results.
  5. Start your demo applications.

Getting Started - Full Guide

  1. Getting Started (Diagram, Configuration, Calibration, Running Demos)

Helpful Tutorials


  • Ubuntu/Debian
  • Leopard OS X 10.5 (PPC/Intel)
  • Windows XP/Vista

Please submit any bugs you may find on CCV's project page

NUI Group