Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity

Bevan, Peggy A., Pantazis, Omiros, Pringle, Holly, Braga Ferreira, Guilherme, Ingram, Daniel J., Madsen, Emily K., Thomas, Liam, Thanet, Dol Raj, Silwal, Thakur, Rayamajhi, Santosh, and others. (2025) Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity. Remote Sensing in Ecology and Conservation, . ISSN 2056-3485. (In press) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:112388)

PDF Author's Accepted Manuscript Language: English Restricted to Repository staff only This work is licensed under a Creative Commons Attribution 4.0 International License.
Contact us about this publication
Official URL: https://zslpublications.onlinelibrary.wiley.com/jo...

Item Type:	Article
Additional information:	For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.
Uncontrolled keywords:	deep neural networks; computer vision; ecological metrics; occupancy; activity patterns; species richness; camera traps
Subjects:	Q Science
Institutional Unit:	Institutes > Durrell Institute of Conservation and Ecology
Former Institutional Unit:	There are no former institutional units.
Funders:	UK Research and Innovation (https://ror.org/001aqnf71)
Depositing User:	Daniel Ingram
Date Deposited:	15 Dec 2025 10:44 UTC
Last Modified:	17 Dec 2025 03:46 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/112388 (The current URI for this page, for reference purposes)

University of Kent Author Information

Ingram, Daniel J..

Creator's ORCID:	https://orcid.org/0000-0001-5843-220X
CReDIT Contributor Roles:	Writing - original draft

Depositors only (login required):

Total Views

Total unique views of this page since July 2020. For more details click on the image.