EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

The Motion Picture: Leveraging Movement to Enhance AI Object Detection in Ecology

Ben Maslen iD, Gordana Popovic, Dadong Wang, Andrew Jansen, David Warton

Ecology and Evolution · 2025-08 · 15 (8)

DOI: 10.1002/ece3.71996 ↗

At a glance

Journal article in Ecology and Evolution, published online on 2025-08-19. Written by Ben Maslen and 4 co-authors. Institution: School of Mathematics and Statistics University of New South Wales Sydney New South Wales Australia. Cited 2 times so far (Crossref); 69 references. The full text is freely available (open access, CC BY 4.0). Funded by: Australian Research Council.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

The rise of AI has seen an explosion in the use of deep learning methods that automate the analysis of image and video data, saving ecologists vast amounts of time and resources. Ecological imagery poses unique challenges; however, with cryptic species struggling to be detected among poor visibility and diverse environments. We propose leveraging movement information to attempt to improve the predictions produced by a high‐performing object detection algorithm. Frame differencing, background subtraction, optical flow and multi‐object tracking are trialed on four diverse datasets containing over 35,000 annotated images sourced from terrestrial, marine and freshwater habitats. We find that leveraging movement information is useful for smaller sized studies and rarer species, however is not needed for well annotated studies (> 400 annotations per class). Out of the methods that utilise movement, we find that a simple ‘differencing’ of neighbouring frames generally performed the best, whilst attempting to track taxa to boost prediction scores performed poorly. Other studies in this area tend to focus only on 1–2 datasets and a single method that utilises movement information, making it difficult for ecologists to generalise results. Our study provides key lessons for ecologists to determine whether it is useful to incorporate methods that leverage movement information when attempting to automatically predict taxa. We offer straightforward code for practical implementation via our GitHub repository, BenMaslen/MCD, along with an evaluation benchmark dataset called ‘Tassie BRUV’ that can be accessed from the Dryad public repository https://doi.org/10.5061/dryad.sbcc2frf7 .

Subjects

Author keywords

artificial intelligencecamera trapscomputer visiondeep learningecologymachine learningmovementunderwater video

Authors and institutions

  • School of Mathematics and Statistics University of New South Wales Sydney New South Wales Australia.
  • Evolution and Ecology Research Centre University of New South Wales Sydney New South Wales Australia.
  • Data61, CSIRO Eveleigh New South Wales Australia.
  • Mark Wainwright Analytical Centre University of New South Wales Sydney New South Wales Australia.
  • Department of Climate Change, Energy, Environment and Water Environmental Research Institute of the Supervising Scientist Darwin Northwest Territories Australia.

ORCID profiles: Ben Maslen

Funding

  • Australian Research Council

Cite

APA

Maslen, B., Popovic, G., Wang, D., Jansen, A., & Warton, D. (2025). The Motion Picture: Leveraging Movement to Enhance AI Object Detection in Ecology. Ecology and Evolution, 15(8). https://doi.org/10.1002/ece3.71996

Vancouver

Maslen B, Popovic G, Wang D, Jansen A, Warton D. The Motion Picture: Leveraging Movement to Enhance AI Object Detection in Ecology. Ecology and Evolution. 2025;15(8). doi:10.1002/ece3.71996

BibTeX
@article{Maslen2025,
  author = {Maslen, Ben and Popovic, Gordana and Wang, Dadong and Jansen, Andrew and Warton, David},
  title = {The Motion Picture: Leveraging Movement to Enhance AI Object Detection in Ecology},
  journal = {Ecology and Evolution},
  year = {2025},
  volume = {15},
  number = {8},
  doi = {10.1002/ece3.71996}
}
Start for free →