(2018) we discuss the Penguin Watch project, which currently operates over 90 cameras in the region 10. A large, collaborative network of remote time-lapse cameras now exists in Antarctica, and in Jones et al. Time-lapse cameras offer a solution to these challenges, and Newbery and Southwell 9 pioneered the use of automated cameras for penguin monitoring. However, the challenges of on-ground monitoring in Antarctica (logistical, practical and financial) have left gaps in data surveys, and the majority of monitoring has occurred on a small scale 8. In order to implement effective mitigation strategies, rigorous monitoring of penguin colonies is required. In the Southern Ocean, two key threats – sea ice change 4, 5 and an expanding krill fishery 6 – have the potential to act synergistically, with a longer ice-free season facilitating a longer harvest 7.

The penguins (Family: Spheniscidae) are amongst the most threatened, facing environmental stressors such as invasive species, overfishing, pollution and climate change 1, 2, 3. Seabird population changes are considered a reflection of changes within the marine environment, making seabird species key indicators of ecosystem health 1, 2. We encourage the use of this large open-source dataset, and the associated processing methodologies, for both ecological studies and continued machine learning and computer vision development. We provide example files for 14 Penguin Watch cameras, generated from 63,070 raw images annotated by 50,445 volunteers. We present two alternative pathways for producing counts: (1) via the Zooniverse citizen science project Penguin Watch and (2) via a computer vision algorithm ( Pengbot), and share a comparison of citizen science-, machine learning-, and expert- derived counts. The latter provide useful summaries of colony spatial structure (which can indicate phenological stage) and can be used to detect movement – metrics which could be valuable for a number of different monitoring scenarios, including image capture during aerial surveys. Here we publish pipelines to process raw time-lapse imagery, resulting in count data (number of penguins per image) and ‘nearest neighbour distance’ measurements. Time-lapse cameras facilitate remote and high-resolution monitoring of wild animal and plant communities, but the image data produced require further processing to be useful.

Time lapse tool license code