embedded-software-laboratory / ssl-vehicle-tracking

Provides ROS2 packages with which vehicles can be tracked on a pressure sensitive surface layer. This is divided into wheel detection and tracking as well as vehicle detection.

SSL Vehicle Tracking

Towards a comprehensive package for roadside vehicle tracking.
Explore the project »

View Demo · Department · Institution

About The Project

This project is a ROS2 implementation of a tracking algorithm that can detect and track vehicles on a pressure-sensitive road surface. We developed this approach as a proof of concept in our paper [1], demonstrating that the road surface itself can be used as a data source for vehicle localization. In addition to the algorithm, the package also provides a visualization tool.

(back to top)

Getting Started

This tool is built with the colcon command line interface like any other ROS2 package. Instructions are found here.

(back to top)

Usage

The tracking pipeline needs a topic of type OccupancyGridMap. An example of a launch file can be found in the package ssl_vehicle_tracking. The provided RVIZ packages are automatically detected.

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Acknowledgments

We acknowledge the financial support for this project by the Collaborative Research Center / Transregio 339 of the German Research Foundation (DFG).

• ROS2
• Stone Soup
• Open CV
• scikit-image
• Readme Template

(back to top)

References

• [1] S. Schäfer, H. Steidl, S. Kowalewski, B. Alrifaee. "Investigating a Pressure Sensitive Surface Layer for Vehicle Localization". In 34rd IEEE Intelligent Vehicles Symposium (IV) 2023, accepted.