Ingrid Brehm

California sea lions (Zalophus californianus) are susceptible to various ocular diseases, with some literature suggesting a heightened risk for those kept in freshwater pools as opposed to saltwater. Given the potential implications of housing conditions on animal health, we wanted to analyze the ocular health of two distinct groups of California sea lions kept at Nuremberg Zoo, one housed in freshwater and the other in saltwater. Data extracted from the animals’ medical records during a ten-year period were used to compare the incidence of eye conditions and other medical conditions observed. The results revealed no significant difference in the overall occurrence of eye diseases between the two environments. However, a distinct seasonal pattern was noted: California sea lions kept in freshwater exhibited a peak in eye disorders during the summer months, while those in saltwater displayed a more uniform distribution of the occurrence of ocular diseases throughout the year. These findings suggest that sun exposure and water quality are potentially more influential factors in the development of ocular diseases in pinnipeds than salinity. Further studies are necessary to elucidate the underlying mechanisms and optimize care practices for these marine mammals.

Automated monitoring systems have become increasingly important for zoological institutions in the study of their animals’ behavior. One crucial processing step for such a system is the re-identification of individuals when using multiple cameras. Deep learning approaches have become the standard methodology for this task. Especially video-based methods promise to achieve a good performance in re-identification, as they can leverage the movement of an animal as an additional feature. This is especially important for applications in zoos, where one has to overcome specific challenges such as changing lighting conditions, occlusions or low image resolutions. However, large amounts of labeled data are needed to train such a deep learning model. We provide an extensively annotated dataset including 13 individual polar bears shown in 1431 sequences, which is an equivalent of 138,363 images. PolarBearVidID is the first video-based re-identification dataset for a non-human species to date. Unlike typical human benchmark re-identification datasets, the polar bears were filmed in a range of unconstrained poses and lighting conditions. Additionally, a video-based re-identification approach is trained and tested on this dataset. The results show that the animals can be identified with a rank-1 accuracy of 96.6%. We thereby show that the movement of individual animals is a characteristic feature and it can be utilized for re-identification.