> **NOTE**: The documentation for users and developers can be found on readthedocs: https://petrack.readthedocs.io/en/latest/
# PeTrack
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.
`PeTrack` (**Pe**destrian **Track**ing) is a tool 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. Individual codes enables personalized trajectories with static information of each participant (e.g. age, gender).
For this reason we are developing the tool named `PeTrack` (**Pe**destrian **Track**ing) 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.
An executable of `PeTrack` is available [here](https://go.fzj.de/petrack-download). The brief [documentation](usage/Usage) of using `PeTrack` cannot answer all questions. Thus you may read also the information [workflow](usage/Workflow-for-performing-experiments-to-be-analyzed-with-PeTrack) and [contact the author](https://go.fzj.de/petrack-boltes) before setting up experiments and automatic extraction with `PeTrack`.
An executable of `PeTrack` is available
[here](https://go.fzj.de/petrack-download). The brief
[documentation](go.fzj.de/petrack-docs) of using `PeTrack` cannot answer all
questions. Thus you may read also [contact the author](https://go.fzj.de/petrack-boltes)
before setting up experiments and automatic extraction with `PeTrack`.
If you run across some issues or bugs when using the software we highly appreciate any reporting.
The most comprehensive insight into the software you will get with the German book:
[Automatische Erfassung präziser Trajektorien in Personenströmen hoher Dichte](https://juser.fz-juelich.de/record/187743/files/FZJ-2015-01334.pdf)
## How to cite
Please cite the general paper and the corresponding software version in your publications if PeTrack helps your research.
In general:
- Boltes, M. and Seyfried, A.: Collecting Pedestrian Trajectories; In: Neurocomputing, Special Issue on Behaviours in Video, vol. 100, pp. 127-133 (2013)
```
@article{BOLTES2013127,
title = {Collecting pedestrian trajectories},
journal = {Neurocomputing},
volume = {100},
pages = {127-133},
year = {2013},
note = {Special issue: Behaviours in video},
issn = {0925-2312},
doi = {https://doi.org/10.1016/j.neucom.2012.01.036},
- https://doi.org/10.5281/zenodo.5078176 (list all versions)
-Croma (March 2022):
```
@software{boltes_maik_2022_6320753,
author = {Boltes, Maik and
Adrian, Juliane and
Boomers, Ann Katrin and
Brualla, Ricardo Martin and
Graf, Arne and
Häger, Paul and
Hillebrand, Daniel and
Kilic, Deniz and
Lieberenz, Paul and
Salden, Daniel and
Schrödter, Tobias},
title = {PeTrack},
month = mar,
year = 2022,
publisher = {Zenodo},
version = {CroMa},
doi = {10.5281/zenodo.6320753},
url = {https://doi.org/10.5281/zenodo.6320753}
}
```
-v0.9 (July 2021):
<p>
<details>
<summary>Click to show how to cite v0.9</summary>
<pre><code>@software{boltes_maik_2021_5126562,
author = {Boltes, Maik and
Boomers, Ann Katrin and
Adrian, Juliane and
Brualla, Ricardo Martin and
Graf, Arne and
Häger, Paul and
Hillebrand, Daniel and
Kilic, Deniz and
Lieberenz, Paul and
Salden, Daniel and
Schrödter, Tobias},
title = {PeTrack},
month = jul,
year = 2021,
publisher = {Zenodo},
version = {v0.9},
doi = {10.5281/zenodo.5126562},
url = {https://doi.org/10.5281/zenodo.5126562}
}
</code></pre>
</details>
</p>
-v0.8:
<p>
<details>
<summary>Click to show how to cite v0.8</summary>
<pre><code>@software{boltes_maik_2021_5109767,
author = {Boltes, Maik and
Adrian, Juliane and
Brualla, Ricardo Martin and
Graf, Arne and
Häger, Paul and
Hillebrand, Daniel and
Kilic, Deniz and
Lieberenz, Paul and
Salden, Daniel and
Schrödter, Tobias and
Seemann, Ann Katrin},
title = {PeTrack},
month = jul,
year = 2021,
publisher = {Zenodo},
version = {v0.8},
doi = {10.5281/zenodo.5109767},
url = {https://doi.org/10.5281/zenodo.5109767}
}
</code></pre>
</details>
</p>
## For new Developers
If you want to us help improve `PeTrack` any contributions are highly appreciated. Some things to help you, to start working on `PeTrack` can be found here:
-[How to setup a development environment](dev/setup)
We apologize that the texts and some comments in the code are in German, we are working on translating it to English to address a wider audience. If you have questions, feel free to ask.
