EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial vision models for the identification of Mediterranean flora: An analysis in four ecosystems

Parminder Kaur iD, Anna Grassi, Federica Bonini, Barbara Valle, Marina Serena Borgatti, Giovanni Rivieccio, Agnese Denaro, Leopoldo de Simone, Emanuele Fanfarillo, Paolo Remagnino

PLOS One · 2025

DOI: 10.1371/journal.pone.0327969 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Parminder Kaur und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Durham University, Durham, United Kingdom. Hauptthemen laut MEDLINE: Ecosystem, Plants, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object identification has been widely used in several applications, utilising the annotated data with bounding boxes to specify each object’s exact location and category in images and videos. However, relatively little research has been conducted on identifying plant species in their natural environments. Natural habitats play a crucial role in preserving biodiversity, ecological balance, and overall ecosystem health. So, effective monitoring of habitats is necessary for safeguarding them, and one way of doing this is by identifying the typical and early warning plant species. Our study quantitatively evaluates the performance of six popular object detection models on our dataset collected in the wild, comprising various plant species from four habitats: screes, dunes, grasslands, and forests. The dataset employed in this work includes the data collected by human operators and the quadrupedal robot ANYmal C. The pre-trained object detection models have been chosen for experiments, and they are fine-tuned on our dataset to achieve better performance. These models incorporate two one-stage (RetinaNet and YOLOv8n), two two-stage (Faster RCNN and Cascade RCNN), and two transformer-based detectors (DETR and Deformable DETR). Extensive experimentation has been performed on the four habitat datasets by applying class balancing and hyperparameter tuning, and the obtained results are discussed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EcosystemPlantsArtificial IntelligenceMediterranean RegionBiodiversityForests

Autor:innen und Institutionen

  • Department of Computer Science, Durham University, Durham, United Kingdom.
  • Department of Agricultural, Food and Environmental Sciences, University of Perugia, Perugia, Italy.
  • NBFC, National Biodiversity Future Center, Palermo, Italy.
  • Department of Life Sciences, Università Degli Studi di Siena, Siena, Italy.
  • Department of Biosciences, Università Degli Studi di Milano, Milano, Italy.
  • Department of Chemical, Physical, Mathematical and Natural Sciences, Università di Sassari, Sassari, Italy.

ORCID-Profile: Parminder Kaur

Förderung

  • H2020 European Research Council

Zitieren

APA

Kaur, P., Grassi, A., Bonini, F., Valle, B., Borgatti, M. S., Rivieccio, G., Denaro, A., de Simone, L., Fanfarillo, E., & Remagnino, P. (2025). Artificial vision models for the identification of Mediterranean flora: An analysis in four ecosystems. PLOS One. https://doi.org/10.1371/journal.pone.0327969

Vancouver

Kaur P, Grassi A, Bonini F, Valle B, Borgatti MS, Rivieccio G, et al. Artificial vision models for the identification of Mediterranean flora: An analysis in four ecosystems. PLOS One. 2025. doi:10.1371/journal.pone.0327969

BibTeX
@article{Kaur2025,
  author = {Kaur, Parminder and Grassi, Anna and Bonini, Federica and Valle, Barbara and Borgatti, Marina Serena and Rivieccio, Giovanni and Denaro, Agnese and de Simone, Leopoldo and Fanfarillo, Emanuele and Remagnino, Paolo},
  title = {Artificial vision models for the identification of Mediterranean flora: An analysis in four ecosystems},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0327969}
}
Kostenlos starten →