Four Mice From Above Dataset

Example_Condition1
Example_Condition7

The “Four Mice From Above” dataset consists of videos of four mice freely moving through a cage that is filmed from above through a transparent lid. The recordings can be used to test multiple-object tracking algorithms with varying occlusions.

The mice were video-recorded under ten different environmental enrichment conditions; i.e., for each video segment different enrichment items were provided to the mice. The more objects were present, the more occlusions could occur. In all occlusion conditions, the cage floor was covered with wooden bedding material and shredded cotton cocoons. In the most crowded occlusion condition, there are a transparent tunnel, a house with a running plate, some paper strips, and paper towel, which offered the mice lots of options to hide from the camera and should be challenging for any tracker. When using the dataset please cite the publication below. The code is available on GitHub.

The related publication has been presented and published at VISAPP 2023, where it received the Best Poster Award. The poster can be found here.
For more information see the publication:

Dolokov, A.; Andresen, N.; Hohlbaum, K.; Thöne-Reineke, C.; Lewejohann, L. and Hellwich, O. (2023). Upper Bound Tracker: A Multi-Animal Tracking Solution for Closed Laboratory Settings. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP, ISBN 978-989-758-634-7; ISSN 2184-4321, pages 945-952.

https://doi.org/10.5220/0011609500003417

 

@conference{visapp23,
author={Alexander Dolokov. and Niek Andresen. and Katharina Hohlbaum. and Christa Thöne{-}Reineke. and Lars Lewejohann. and Olaf Hellwich.},
title={Upper Bound Tracker: A Multi-Animal Tracking Solution for Closed Laboratory Settings},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP,},
year={2023},
pages={945-952},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011609500003417},
isbn={978-989-758-634-7},
issn={2184-4321},
}