Contributing to the OpenPTrack codebase 
The OpenPTrack source code and most developer documentation is available on GitHub. Pull requests and contributions are welcome.
Please send an introductory message about your interests. (You can email us at openptrack@gmail.com.)
Forking / Extending OpenPtrack
OpenPTrack is licensed with a BSD-style license with an attribution requirement, with some exceptions noted below.
Dependencies
OpenPTrack is built on other open source libraries: the Point Cloud Library (PCL) and Robot Operating System (ROS). As OpenPTrack is under heavy development, changes in its architecture and API may occur. For more information, please see the Roadmap.
OpenPTrack
If you use our code, please cite:
—M. Munaro, F. Basso and E. Menegatti. OpenPTrack: Open Source Multi-Camera Calibration and People Tracking for RGB-D Camera Networks. Journal on Robotics and Autonomous Systems, vol. 75, part B, pp. 525-538, Elsevier, 2016.
—M. Munaro, A. Horn, R. Illum, J. Burke and R. B. Rusu. OpenPTrack: People Tracking for Heterogeneous Networks of Color-Depth Cameras. In IAS-13 Workshop Proceedings: 1st Intl. Workshop on 3D Robot Perception with Point Cloud Library, pp. 235-247, Padova, Italy, 2014.
—M. Munaro and E. Menegatti. Fast RGB-D People Tracking for Service Robots. Journal on Autonomous Robots, vol. 37(3), pp. 227-242, Springer, 2014.
OpenPTrack v2 Pose Recognition
Users should cite:
—M. Carraro, M. Munaro, J. Burke, and E. Menegatti, 2017. Real-time marker-less multi-person 3D pose estimation in RGB-Depth camera networks. arXiv preprint arXiv:1710.06235.
As well as the OpenPose papers:
—Z. Cao, T. Simon, S. E. Wei, and Y. Sheikh, 2016. Realtime multi-person 2d pose estimation using part affinity fields. arXiv preprint arXiv:1611.08050.
—T. Simon, H. Joo, I. A. Matthews, and Y. Sheikh, 2017, July. Hand Keypoint Detection in Single Images Using Multiview Bootstrapping. In CVPR (Vol. 1, p. 2).
Note that the OpenPose library used in pose recognition does not allow commercial repackaging of OpenPTrack pose recognition capabilities; please contact the CMU OpenPose team for a license.
OpenPTrack v2 Object Recognition
Users should cite the Yolo paper:
— J. Redmon, and A. Farhadi. YOLO9000: better, faster, stronger. arXiv preprint (2017).
OpenPTrack v2 Face Recognition
Users should cite:
—K. Koide, E. Menegatti, M. Carraro, M. Munaro, and J. Miura, 2017, People Tracking and Re-Identification by Face Recognition for RGB-D Camera Networks2017. ECMR 2017.
As well as:
—B. Amos, B. Ludwiczuk, M. Satyanarayanan, Openface: A general-purpose face recognition library with mobile applications, CMU-CS-16-118, CMU School of Computer Science, Tech. Rep., 2016.
Unless otherwise stated, source code for OpenFace and trained Torch and Python model files are copyright Carnegie Mellon University, and are used under the Apache 2.0 License.
