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

The peer-reviewed publication for this dataset has now been published in Animals, an MDPI journal, and can be accessed here: https://doi.org/10.3390/ani13050801. Please cite this when using the dataset.

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.