First Steps in Open SourcePosted: March 17, 2011
I am happy to finally announce a first (very early) release of the Traffic Intelligence open source project, a set of tools for transportation analysis, in particular road traffic. The tool revolves around the most typical transportation data type, trajectories, i.e. temporal series of positions. The original work targeted automated road safety analysis using video sensors. This project is at a very early stage and does not really provide any finished tool. It contains:
- pieces of C++ code under the c directory, mostly examples related to the use of computer vision libraries, namely OpenCV and KLT
- Python modules that provide classes for trajectories and moving objects (objects with some characteristics and a trajectory), as well as some basic code for simple traffic engineering problems (fundamental diagram and traffic signal timing).
The main use case and example for now is to load and analyze trajectory data from the NGSIM project. The image on the right is a plot of the first 100 trajectories of the US 101 dataset.
More technical information is available on the code repository hosted at bitbucket, and future news will be posted there. The code is licensed under the MIT open source license. I would be happy to hear from you if you make use of the code, or are interested in collaborating and contributing.