Hochschule Karlsruhe Hochschule Karlsruhe - University of Applied Sciences
Open navigation Close navigation
Hochschule Karlsruhe Hochschule Karlsruhe - University of Applied Sciences

Intelligent Systems Research Group

MULTIPLE

Multi-View Intensity-Depth Data Set for Top-View Indoor
People Detection

Authors:
Johannes Wetzel, M.Sc.
Prof. Dr. Astrid Laubenheimer

Contact:
For questions regarding the download of the dataset
feel free to contact isrgspam prevention@h-ka.de.

Description

The MULTIPLE data set covers the scenario of top-view people detection using multiple depth sensors with overlapping fields of view. The data set contains footage from an indoor office scene and is recorded by three low-resolution commodity stereo-vision-based depth sensors.

The sensors have a top-view on the scene, are mounted at a height of three meters, and have fields of view with a significant joint overlap. They cover a visible area of approximately 20 m² with up to six individual people present in the scene, entering and leaving the visible area multiple times. The data set consists of 2800 annotated frames, captured with a resolution of 376 × 240 pixel each, providing raw rectified stereo image pairs as well as disparity maps obtained by block matching. In total we annotated the ground floor locations of 12000 targets. In addition we associated each detection with a track to allow a complete evaluation of the detection and tracking.

Cite & Bibtex

If you use the MULTIPLE data set please cite the primary article, where MULTIPLE was introduced:

Wetzel J., Laubenheimer A., and Heizmann M.
Joint Probabilistic People Detection in Overlapping Depth Images
In IEEE Access, vol. 8, 2020, doi: 10.1109/ACCESS.2020.2972055 [pdf]

@ARTICLE{8985332,
  author={J. {Wetzel} and A. {Laubenheimer} and M. {Heizmann}},
  journal={IEEE Access},
  title={Joint Probabilistic People Detection in Overlapping Depth Images},
  year={2020},
  volume={8},
  number={},
  pages={28349-28359},
  abstract={},
  keywords={},
  doi={10.1109/ACCESS.2020.2972055},
  ISSN={2169-3536},
  month={}
}

How to get the data?

If you are interested in using the data set, feel free to send your request via e-mail to isrgspam prevention@h-ka.de

Please include the name of your organisiation, a contact person and the purpose of the usage of the data set. After accepting the terms of the license we will provide you a personalized download link.

License & Data Protection

MULTIPLE is available for free for non-commercial use under the provided license.

The data has been collected in compliance with the law by obtaining the consent of the persons concerned under the data protection information. Please note that the consent can be withdrawn at any time. This may result to the data being deleted by the licensee. For details see the license.