Automatic Extraction of Pedestrian Trajectories from Video Recordings
For the understanding of the dynamics inside crowds reliable empirical data are needed enabling an increase of safety and comfort for pedestrians and the design of models reflecting the real dynamics. The existing database is small, sometimes inaccurate and highly contradictory. Manual procedures for collecting this data are very time-consuming and usually do not supply sufficient accuracy in space and time.
For this reason we are developing the tool named PeTrack (Pedestrian Tracking) to automatically extract accurate pedestrian trajectories from video recordings. The joint trajectories of all pedestrians provide data like velocity, flow and density at any time and position. With such a tool extensive experimental series with a large number of persons can be analyzed. Individual codes enables personalized trajectories with static information of each participant (e.g. age, gender).
The program has to deal with wide angle lenses and a high density of pedestrians. Lens distortion and perspective view are taken into account. The procedure includes calibration, recognition, tracking and height detection.
Different kinds of markers (e.g. with height information, head direction, individual code) are implemented. With a stereo camera more accurate height measurements and also markerless tracking is possible.
The source code as well as a precompiled executable of PeTrack are available. The brief documentation of using PeTrack cannot answer all questions. Thus you may contact the author before setting up experiments and automatic extraction with PeTrack.
How to cite
Please cite the general paper and the corresponding software version in your publications if PeTrack helps your research.
- Boltes, M. and Seyfried, A.: Collecting Pedestrian Trajectories; In: Neurocomputing, Special Issue on Behaviours in Video, vol. 100, pp. 127-133 (2013). https://doi.org/10.1016/j.neucom.2012.01.036
Software version (v0.9):
- Boltes, M., Boomers, A. K., Adrian, J., Brualla, R. M., Graf, A., Häger, P., Hillebrand, D., Kilic, D., Lieberenz, P., Salden, D., & Schrödter, T. (2021). PeTrack (v0.9) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.5126562
A list of all versions can be found here. To find your corresponding version, check the `about` menu or look into the terminal output of PeTrack.