PolarBearVidID: A Video-Based Re-Identification Benchmark Dataset for Polar Bears

PolarBearVidID: A Video-Based Re-Identification Benchmark Dataset for Polar Bears

PolarBearVidID includes 13 individual polar bears housed in six institutions. Each identity has 110 sequences on average. The maximum length of the sequences is 8 seconds, respectively 100 frames at a frame rate of 12.5 frames per second. The average length of the sequences is 96.69 images. In total, the dataset includes 1431 sequences. The resolution of the images is set to 256 x 128 pixels. Finally, PolarBearVidID is the first dataset to enable utilizing the movement of a non-human species as a feature for the task of re-identification.


Example sequences

Vera (Nuremberg)
Nanuq (Nuremberg)

Tonja (Berlin)
Hertha (Berlin)


Our polar bears

ID Name Gender Birth Zoo Sequences
00 Vera Female 2002 Nuremberg 123
01 Nanuq Male 2007 Nuremberg 105
02 Tonja Female 2009 Berlin 108
03 Hertha Female 2018 Berlin 118
04 Nora Female 2013 Vienna 104
05 Finja Female 2019 Vienna 107
06 Larissa Female 1990 Neumünster 107
07 Vitus Male 2000 Neumünster 104
08 Lloyd Male 2000 Karlsruhe 120
09 Charlotte Female 2014 Karlsruhe 112
10 Nana Female 2019 Hannover 119
11 Milana Female 2009 Hannover 104
12 Sprinter Male 2007 Hannover 100