loading page

Counting animals in aerial images with a crowd counting model
  • +2
  • Yifei Qian,
  • Grant Humphries,
  • Philip Trathan,
  • Andrew Lowther,
  • Carl Donovan
Yifei Qian
University of St Andrews

Corresponding Author:[email protected]

Author Profile
Grant Humphries
Hidef Aerial Surveying Ltd
Author Profile
Philip Trathan
British Antarctic Survey
Author Profile
Andrew Lowther
Norwegian Polar Institute
Author Profile
Carl Donovan
University of St Andrews
Author Profile


1. Animal abundance estimation is increasingly based on drone or aerial survey photography. Manual post-processing has been used extensively, however volumes of such data are increasing, necessitating some level of automation, either for complete counting, or as a labour-saving tool. Any automated processing can be challenging when using the tools on species that nest in close formation such as Pygoscelid penguins. 2. We present here an adaptation of state-of-the-art crowd-counting methodologies for counting of penguins from aerial photography. 3. The crowd-counting model performed significantly better in terms of model performance and computational efficiency than standard Faster RCNN deep-learning approaches and gave an error rate of only 0.8 percent. 4. Crowd-counting techniques as demonstrated here have the ability to vastly improve our ability to count animals in tight aggregations, which will demonstrably improve monitoring efforts from aerial imagery.
14 Sep 2022Submitted to Ecology and Evolution
15 Sep 2022Submission Checks Completed
15 Sep 2022Assigned to Editor
16 Sep 2022Reviewer(s) Assigned
28 Oct 2022Review(s) Completed, Editorial Evaluation Pending
01 Nov 2022Editorial Decision: Revise Minor
05 Dec 20221st Revision Received
06 Dec 2022Submission Checks Completed
06 Dec 2022Assigned to Editor
06 Dec 2022Review(s) Completed, Editorial Evaluation Pending
07 Dec 2022Reviewer(s) Assigned
28 Jan 2023Editorial Decision: Revise Minor
14 Feb 20232nd Revision Received
15 Feb 2023Submission Checks Completed
15 Feb 2023Assigned to Editor
15 Feb 2023Review(s) Completed, Editorial Evaluation Pending
22 Feb 2023Editorial Decision: Accept