Software Framework for markerless object tracking released

06/16/2009 : 15:39

The CoTeSys project "ITrackU - Image-based Tracking and Understanding" is developing an integrated software framework for real-time visual tracking of moving objects, human bodies as well as faces or gaze named OpenTL.

The CoTeSys project  "ITrackU - Image-based Tracking and Understanding"is developing an integrated software framework for real-time visual tracking of moving objects, human bodies as well as faces or gaze named OpenTL.

This software package for model-based, markerless object tracking applications ranges from single-camera and mono-modal scenarios, up to complex configurations involving multiple targets, cameras and visual modalities. 

Nowadays many different state-of-the-art visual tracking approaches have been developed, covering a wide variety of application scenarios. Each one follows individual requirements, and benefits from different aspects of the underlying problem and prior information, while most of the time being specific to a single scenario.

"Despite the huge literature available, to our knowledge no really general-purpose library has been yet developed for tracking marker-less objects. With such a target in mind we have developed OpenTL (Open Tracking Library), a general-purpose library for markerless tracking that provides a user-friendly high-level application programming interface (API) for the widest variety of methods and applications", explains Prof. Dr.-Ing. Alois Knoll, project leader of ITrackU, from the Chair for Robotics and Embedded Systems of TUM-Informatik.

The algorithmic foundations for OpenTL have been developed since 2002 at
TUM-Informatik VI (Robotics and Embedded Systems), capitalizing on years
of experience in the field, finally leading to the creation of its C++ architecture, since May 2007. Since January 2008, the CoTeSys project ITrackU is making intensive use and development of the library, and a number of significant improvements for enhanced usability and code efficiency have been made.

 The objective of OpenTL is to provide a highly structured, modular and scalable programming environment, with all building blocks  required for a wide range of applications, focusing on (but not limited to) the applications within the demonstration scenarios. In particular, an edge-based matching modality is provided, that can be combined with color-based method, in order to develop more robust and general-purpose tracking applications.

Further informationen is available here: opentl-dev@remove-this.mailknoll.in.tum.de.