Animal welfare assessments increasingly aim to quantify enclosure use and activity to support naturalistic behavior and improve Quality of Life (QoL). Traditionally, this is achieved through manual observations, which are time-consuming, subject to observer bias, and limited in temporal resolution due to short observation periods. Here, we compared manual tracking using ZooMonitor with automated pose estimation (SLEAP) in a mother–son pair of black-headed spider monkeys (Ateles fusciceps) at Aalborg Zoo. We collected manual observations on six non-consecutive days (median daily duration: 62 min, mean: 66 min, range: 52–90 min) and visualized this as spatial heatmaps. We applied pose estimation to the same video footage, tracking four body parts to generate corresponding heatmaps. Across most days, the methods showed strong agreement (overlap 83–99%, Pearson’s r = 0.93–1.00), with both highlighting core activity areas on the floor near the central climbing structures and by the door with feeding gutters. Both methods also produced comparable estimates of time spent being active, with no significant difference across days (p = 0.952). Our results demonstrate that computer vision technology can provide a reliable and scalable tool for monitoring enclosure use and activity, enhancing the efficiency and consistency of zoo-based welfare assessments while reducing reliance on labor-intensive manual observations.

The pygmy hippopotamus (Choeropsis liberiensis, Morton, 1849) is classified as Endangered by the International Union for the Conservation of Nature (IUCN). Compared to other large, threatened mammals, this species remains relatively understudied and new findings indicate potential welfare concerns, emphasizing the need for further research on the species welfare in zoological institutions. One approach to improving welfare in captivity is through environmental enrichment. This study investigated the effects of olfactory enrichment on three individual pygmy hippopotamuses through behavioral analysis and heat-map visualization. Using continuous focal sampling, several behaviors were influenced by the stimuli, with results showing a general decrease in inactivity and an increase in environmental engagement and interaction, particularly through scenting behavior. To further enhance behavioral quantification, machine learning techniques were applied to video data, comparing manual and automated behavior classification using the pose estimation program SLEAP. Four behaviors Standing, Locomotion, Feeding/Foraging, and Lying Down were compared. A confusion matrix, time budgets, and Kendall’s Coefficient of Concordance (W) were used to assess agreement between methods. The results showed a strong and moderate agreement between manual and automated annotations, for the female and calf, respectively. This demonstrates the potential of automation to complement behavioral observations in future welfare monitoring.

Animal welfare assessments increasingly aim to quantify enclosure use and activity to support naturalistic behavior and improve Quality of Life (QoL). Traditionally, this is achieved through manual observations, which are time-consuming, subject to observer bias, and limited in temporal resolution due to short observation periods. Here, we compared manual tracking using ZooMonitor with automated pose estimation (SLEAP) in a mother–son pair of black-headed spider monkeys (Ateles fusciceps) at Aalborg Zoo. Manual observations were collected on six non-consecutive days (median daily duration: 62 min, mean: 66 min, range: 52–90 min) and visualized as spatial heatmaps. Pose estimation was applied to the same video footage, tracking four body parts to generate corresponding heatmaps. Across most days, the methods showed strong agreement (overlap 83–99%, Pearson’s r = 0.93–1.00), with both highlighting core activity areas on the floor near the central climbing structures and by the door with feeding gutters. Both methods also produced comparable estimates of time spent active, with no significant difference across days (p = 0.952). These results demonstrate that computer vision technology can provide a reliable and scalable tool for monitoring enclosure use and activity, enhancing the efficiency and consistency of zoo-based welfare assessments while reducing reliance on labor-intensive manual observations.

Monitoring both captive animals and wild populations is necessary to ensure adequate animal welfare and wildlife conservation. Existing monitoring tools, e.g., camera traps, enable surveillance, yet analysis can prove time-consuming and labor-intensive if handled manually. The automated nature of machine learning (ML) reduces observer bias and manual workload and improves assessment capacity of behavioral monitoring tools that are often used by staff at zoological institutions. This study investigated the activity and space use of three captive jaguars (Panthera onca) through automated individual recognition, activity tracking, and heatmap visualization using an ML model trained on video footage. In total, 123.8 h of video footage was recorded of the jaguar enclosure in Randers Regnskov, Tropical Zoo. The ML model analyzed all videos containing jaguars from one day. The model achieved satisfactory performance based on its evaluation metrics (mean average precision, recall, precision, and F1-score). The ML model showed repeated movement tracks within specific enclosure areas. The jaguars exhibited significantly more inactive than active behavior and did not seem to exhibit natural bimodal nocturnal or crepuscular hunter activity patterns. It should be stated that, due to the small sample size of only three jaguars and 24 analyzed hours, this study is a proof-of-concept to demonstrate the potential of ML methods as valuable tools for individual recognition, activity tracking, and monitoring of space use to aid in future animal welfare monitoring.

This study evaluates activity patterns and determines optimal observation periods for assessing the welfare of lowland tapirs (Tapirus terrestris L.) housed in the following two Danish zoological institutions: Aalborg Zoo and Randers Regnskov. The objectives were to identify the most efficient time window for welfare assessments, determine whether machine learning (ML) could support behavioral evaluations by providing automated estimates of activity, and examine whether automated pose-based tracking could serve as a proxy for manual ethogram observations. Behavioral data were collected using standardized ethograms from wildlife camera footage recorded over 72 h. Lowland tapirs were generally more active during daytime, with individuals at Aalborg Zoo showing peak activity between 07:00 and 14:00, while those at Randers Regnskov were most active between 12:00 and 18:00. Activity patterns differed between institutions, with Aalborg individuals displaying concentrated activity peaks and Randers individuals showing more evenly distributed activity. A preliminary ML analysis using the pose-estimation tool SLEAP demonstrated that movement-based activity estimates closely matched manually coded data, suggesting that automated tracking may offer an efficient and non-invasive tool for welfare monitoring. The findings highlight the potential for integrating automated analysis into routine welfare assessments of zoo-housed animals.

Behavioral observation is central to animal welfare assessment in zoological institutions, but manual observation is time-consuming and difficult to apply continuously. We developed and applied a LabGym-based workflow for automated behavioral monitoring of captive lions (Panthera leo). Development footage from three Danish zoological institutions was used to train a lion detector and a seven-class behavior categorizer; video collected on 22–28 December 2025 was temporally held out from model development and used for applied validation. Detector performance was moderate (bounding-box AP 47.1%; segmentation AP 41.6%), while the internal categorizer validation reached 0.62 accuracy and weighted F1. In the held-out validation, 52.6% of manually annotated lion-time received a retained pipeline prediction. Fine-scale end-to-end accuracy was 0.231 and increased to 0.440 when calculated only on covered lion-time. Grouping behaviors as active, inactive/maintenance, and pacing-like locomotion increased these values to 0.317 and 0.602, respectively. Coverage varied substantially among institutions (33.8–59.8%) and was particularly low for cubs and nighttime footage. Although model macro-F1 exceeded simple majority-class baselines, end-to-end accuracy did not. The workflow demonstrates the potential of computer-vision approaches for scalable behavioral quantification and future welfare assessment in zoological settings, while highlighting the importance of accounting for prediction coverage and classification performance when interpreting automated behavioral data.