SwisTrack is a powerful tool for tracking robots, humans, animals and objects using a camera or a recorded video as input source. It uses Intel’s OpenCV library for fast image processing and contains interfaces for USB, FireWire and GigE cameras, as well as AVI files.

The architecture of SwisTrack is very flexible and therefore allows the user to track (marked and marker-less) objects in many situations. So-called components are stuck together (like Lego bricks) and configured. Each component then performs one processing step, which can be visualized in real-time. SwisTrack already comes with a series of components, but for specialized tasks, programmers are free to implement their own components. Position and trajectory information can be retrieved via TCP/IP in NMEA 0183 format. Such data can easily be recorded for post-processing, or used in a real-time fashion.

SwisTrack has mainly been developed by the Distributed Intelligent Systems and Algorithms Laboratory (DISAL) and the LPM Vision Group at EPFL in Lausanne, Switzerland.

Detailed information about SwisTrack is available in the SwisTrack wikibook. The SwisTrack project is kindly hosted at SourceForge.net. Please click here to proceed to the download page.The source code is available via sourceforge’s SVN server.

Please report bugs using the bug tracking system. Have a look at the FAQ item “How to submit a bug” first (Report a bug now).

You can subscribe to the Swistrack mailing list to be informed about new releases and bug fixes.

•  SwisTrack 4: Doumentation (wikibook)
• SwisTrack 4: Tracking cockroaches (video)
• SwisTrack 4: Poster
• SwisTrack 3: Demo Tracking of 10 cockroaches and 1 Insbot, partially occluded by semi-transparent shelters
• SwisTrack 3: Guided tour (video)  

Team and Collaborators

• Nikolaus Correll
• Thomas Lochmatter
• Pierre Roduit

Sponsors

EC FP6, SNSF

Publications