Plittersdorf Dataset

Instance Annotation Example

The Plittersdorf dataset was captured using the SOCRATES stereo camera trap in early 2022 in the wildlife park Plittersdorf, Bonn Germany. It consists of 221 stereo videos of European fallow deer (Dama dama) and Sika deer (Cervus nippon), each 25 seconds in length with 30 frames per second. A subset of images is labeled with a total of 546 instance masks in the COCO JSON format. If you use this dataset, please cite the appropriate Zenodo entries. If you refer to the methodology used to obtain this dataset, please cite the publication indicated below.


This work is partially funded by the German Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung (BMBF,, Bonn, Gemany (AMMOD - Automated Multisensor Stations for Monitoring of BioDiversity: FKZ 01LC1903B). This funding is gratefully acknowledged.

We thank Vincent Mainzer and the team of the Tierpark Plittersdorf for their cooperation by hosting the camera trap hardware on site.


In plaintext:

Haucke, T., Kühl, H. S., & Steinhage, V. (2022). SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision. Sensors, 22(23).

In BibTeX:

author = {Haucke, Timm and Kühl, Hjalmar S. and Steinhage, Volker},
title = {SOCRATES: Introducing Depth in Visual Wildlife Monitoring Using Stereo Vision},
journal = {Sensors},
volume = {22},
year = {2022},
number = {23},
article-number = {9082},
url = {},
issn = {1424-8220},
doi = {10.3390/s22239082}