Automated Video-Based Analysis Framework for Behavior Monitoring of Individual Animals in Zoos Using Deep Learning—A Study on Polar Bears

Abstract

The monitoring of animals under human care is a crucial tool for biologists and zookeepers to keep track of the animals’ physical and psychological health. Additionally, it enables the analysis of observed behavioral changes and helps to unravel underlying reasons. Enhancing our understanding of animals ensures and improves ex situ animal welfare as well as in situ conservation. However, traditional observation methods are time- and labor-intensive, as they require experts to observe the animals on-site during long and repeated sessions and manually score their behavior. Therefore, the development of automated observation systems would greatly benefit researchers and practitioners in this domain. We propose an automated framework for basic behavior monitoring of individual animals under human care. Raw video data are processed to continuously determine the position of the individuals within the enclosure. The trajectories describing their travel patterns are presented, along with fundamental analysis, through a graphical user interface (GUI). We evaluate the performance of the framework on captive polar bears (Ursus maritimus). We show that the framework can localize and identify individual polar bears with an F1 score of 86.4%. The localization accuracy of the framework is 19.9±7.6 cm, outperforming current manual observation methods. Furthermore, we provide a bounding-box-labeled dataset of the two polar bears housed in Nuremberg Zoo.

Development of a Slow Loris Computer Vision Detection Model

“…This study lays a foundation for the welfare improvement of endangered animals, such as slow loris, which have received less attention and are relatively backward in protection measures. In the future, the authors will continue to optimize the YOLOv5-CBAM + TC model, expand its application range from captivity to the wild, and combine it with other deep learning technologies to realize the individual identification [ 32 ] and behavior recognition [ 33 ] of the slow loris.…”

Power Up: Combining Behavior Monitoring Software with Business Intelligence Tools to Enhance Proactive Animal Welfare Reporting

“…It has been argued that these technologies are allowing farmers to build "digital representations" of their animals (Norton et al, 2019). While the realization of a similar smart zoo concept is likely to be some years away, the recent study by Zuerl et al [47] developed algorithms for automated video-based monitoring of polar bears at Nuremberg Zoo, which is an exciting development that hints at a future with more robust data collection than has hitherto been possible. The growth of automated monitoring through sensors and cameras in zoos has the potential to transform our ability to proactively monitor welfare [33] beyond our current limitations in staff availability and schedules, including during overnight time periods when staff are not present and live observations are impractical, but we will need corresponding advances in our analytics capabilities to harness these technologies.…”

Integrating remote international experience and community engagement into course‐based animal behavior research

“…Our work builds upon previous published activities that have incorporated video footage into animal behavior research and teaching (Bain et al, 2021 ; Grigg et al, 2021 ; Littman & Moore, 2016 ; Nunes et al, 2021 ; Zuerl et al, 2022 ). Previous studies have incorporated videos from camera traps in the field (Burger et al, 2021 ) or in zoos (Hahn‐Klimroth et al, 2021 ), citizen science contributions (Oberbauer et al, 2021 ), or targeted footage of wild (Bain et al, 2021 ), domesticated (Grigg et al, 2021 ; Vega et al, 2010 ), or laboratory animals (Kimura et al, 2014 ).…”