The recent introduction of low-cost devices for real-time acquisition of dense 3-D range imaging (RI) streams has attracted a great deal of attention. The Range Imaging Toolkit (RITK) provides a powerful yet intuitive software platform that facilitates the development of range image stream applications. RITK puts emphasis on real-time processing of range image streams and proposes the use of a dedicated pipeline mechanism. Furthermore, we introduce a powerful and convenient interface for range image processing on the graphics processing unit (GPU). Being designed thoroughly and in a generic manner, the toolkit is able to cope with the broad diversity of data streams provided by available RI devices and can easily be extended by custom range imaging sensors or processing modules. RITK is an open source project. It is an object-oriented, cross-platform toolkit written in C++, that can be used as a regular library as well as an application framework for rapid development.

In our internal experience, RITK proved to greatly reduce the time required to develop range image stream applications. Hence, we feel confident that other researchers in the rapid growing community will also benefit from it.
 

04/19/2012   RITK released (1.1).

10/05/2011   RITK released (1.0).

10/05/2011   RITK presented at the International Workshop on Vision, Modeling and Visualization (VMV), 2011.
 

An overview of RITK and its features is given in our paper, see section Citation. The paper is a good starting point when you decide to work with RITK. You may also want to have a look at the RITK presentation given at the International Workshop on Vision, Modeling and Visualization (VMV), 2011.
 

The current release (see section Download) includes the following plugins:

• Source plugins:
  • Kinect Player

• Filter plugins:
  • TimeAveraging

• Application plugins
  • Visualization

Filters presented at CDC4CV will be provided soon. You may write us an email to get informed.

Please be aware of: This software is under development. Expect no perfect stability and user friendlyness. Only a very rudimentary manual is provided. No warranty or any other guaranties are given. Use the software only for research purposes.

We invite you to notify us via email that you downloaded the programm. You will be then be added to the mailing list and kept on track about future versions and bugfixes. You might also want to tell us the purpose you're using the framework for - we are interested in how RITK might be used.

Source Code (RITK 1.1)

Windows binaries (RITK 1.1, 32bit, VC9, CUDA 4.1, Qt 4.7.2)

Please note that the RI simulator plugin shipped with this release of RITK depends on the 3rd party library libnoise. However, the 32bit VC9 built libnoise.dll of this library is erroneously classified as malware by the avira anti-virus software. You can download the pre-built binary here, or have to build it on your own if you want to use the RI simulator plugin

If you do not have a RI sensor available, you may want to download some sample data:

- SceneKinect.ris
- PhantomsKinect.ris
- PhantomsPMDCamCube3.ris
 

A short and preliminary documentation including step-by-step build instructions and a basic tutorial for writing your own RITK plugin is given HERE. We recommend to read the documentation before starting to work with RITK.
 

RITK employs the following third party libraries:

• Qt (LGPL license), http://qt.nokia.com/products
• Insight Segmentation and Registration ToolKit (ITK), http://www.itk.org
• Visualization ToolKit (VTK), http://www.vtk.org

For license and copyright details on RITK and the above listed third party libraries see the Copyright folder in your RITK installation directory.

We will set up an RITK version control system soon. For now, if you have questions on the use of RITK, encountered bugs, have suggestions for improvements or search for a collaboration, please send us an email.

An up-to-date list of known bugs and issues can be found HERE.
 

RITK was developed at the Pattern Recognition Lab at the Friedrich-Alexander-Universität Erlangen-Nürnberg. For an overview of RI research at the PRL, please see the website of the Medical Image Registration Group (MIRG).