Reliable and efficient integration of AI into camera traps for smart wildlife monitoring based on continual learning

Delia Velasco-Montero, Jorge Fernández‐Berni, Ricardo Carmona‐Galán, Ariadna Sanglas, Francisço Palomares

Ecological Informatics 2024 article cited by 39

Source Open-access PDF More in Climate & Environment

importance 4/10 solved Advanced Neural Network Applications wildlife conservation stage: research open-source model

Problem

Camera traps produce large image volumes that normally require off-site manual or desktop processing, hindering reliable on-site wildlife monitoring.

Why it matters

Scalable, affordable automated monitoring is essential for conservation and ecological research in remote field conditions.

What the AI did

The authors built sub-$100 smart camera trap prototypes using transfer learning, explainable AI and continual learning to run reliable inference on-site, plus two public datasets of 17k+ images.

Results

10% higher F1-score on-site than MegaDetector run off-site on a desktop; prototypes under $100 bill of materials; 17k+ image datasets

Impact

Peer-reviewed prototypes with a concrete benchmark improvement over an external baseline.

Record

Venue	Ecological Informatics
Published	2024
Work type	article
Authors	Delia Velasco-Montero, Jorge Fernández‐Berni, Ricardo Carmona‐Galán, Ariadna Sanglas, Francisço Palomares
Citations	39 (OpenAlex, at import time)
References	85
Model or method	not stated in source
Organization	not stated in source
Primary source	https://doi.org/10.1016/j.ecoinf.2024.102815
Open access	gold
Keywords	camera traps, continual learning, embedded AI, wildlife monitoring, F1-score

Importance rating

4 / 10

real but narrower advance

Off-site processing hinders reliable on-site wildlife monitoring needed for conservation and ecology; abstract states no scale of the monitoring problem.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Climate & Environment

#	Paper	Year	Citations	Importance
1	Learning skillful medium-range global weather forecasting Rémi Lam, Álvaro Sánchez‐González, Matthew Willson, Peter Wirnsberger,...	2023	1,416	8
2	Accurate medium-range global weather forecasting with 3D neural networks Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, Qi Chuan...	2023	1,631	8
3	FuXi: a cascade machine learning forecasting system for 15-day global weather forecast Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Qi Yuan,...	2023	355	8
4	Skilful nowcasting of extreme precipitation with NowcastNet Yuchen Zhang, Mingsheng Long, Kaiyuan Chen, Lanxiang Xing, Ronghua Jin...	2023	451	8
5	Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects Natei Ermias Benti, Mesfin Diro Chaka, Addisu Gezahegn Semie	2023	378	8