EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance Analysis of Real-Time Detection Transformer and You Only Look Once Models for Weed Detection in Maize Cultivation

Oscar Leonardo García-Navarrete, Jesús Hernán Camacho-Tamayo, Anibal Bregon Bregon, Jorge Martín-García, Luis Manuel Navas-Gracia

Agronomy · 24.03.2025 · 15 (4) · 796

DOI: 10.3390/agronomy15040796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 24.03.2025. Verfasst von Oscar Leonardo García-Navarrete und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weeds are unwanted and invasive plants characterized by their rapid growth and ability to compete with crops for essential resources such as space, water, nutrients, and sunlight. This competition has a negative impact on crop quality and productivity. To reduce the influence of weeds, precision weeding is used, which uses image sensors and computational algorithms to identify plants and classify weeds using digital images. This study used images of maize (Zea mays L.) to detect four types of weeds (Lolium rigidum, Sonchus oleraceus, Solanum nigrum, and Poa annua). For this purpose, YOLO (You Only Look Once) architectures, YOLOv8s, YOLOv9s, YOLOv10s, and YOLOv11s versions, were trained and compared, along with an architecture based on RT-DETR (Real-Time Detection Transformer), version RT-DETR-1. The YOLO architectures are noted for their real-time detection efficiency, and RT-DETR-l allows evaluation of the impact of an architecture that dispenses with Non-Maximum Suppression (NMS). The YOLOv9s model had the best overall performance, achieving a mAP@0.5 of 0.834 in 60 epochs and an F1-score of 0.78, which demonstrates a optimal balance between accuracy and recall, although with less confidence in its predictions. On the other hand, the RT-DETR-l model stood out for its efficiency in convergence, reaching a competitive performance in only 58 epochs with a mAP@0.5 of 0.828 and an F1-score of 0.80.

Förderung

  • European Union

Zitieren

APA

García-Navarrete, O. L., Camacho-Tamayo, J. H., Bregon, A. B., Martín-García, J., & Navas-Gracia, L. M. (2025). Performance Analysis of Real-Time Detection Transformer and You Only Look Once Models for Weed Detection in Maize Cultivation. Agronomy, 15(4), 796. https://doi.org/10.3390/agronomy15040796

Vancouver

García-Navarrete OL, Camacho-Tamayo JH, Bregon AB, Martín-García J, Navas-Gracia LM. Performance Analysis of Real-Time Detection Transformer and You Only Look Once Models for Weed Detection in Maize Cultivation. Agronomy. 2025;15(4):796. doi:10.3390/agronomy15040796

BibTeX
@article{GarcaNavarrete2025,
  author = {García-Navarrete, Oscar Leonardo and Camacho-Tamayo, Jesús Hernán and Bregon, Anibal Bregon and Martín-García, Jorge and Navas-Gracia, Luis Manuel},
  title = {Performance Analysis of Real-Time Detection Transformer and You Only Look Once Models for Weed Detection in Maize Cultivation},
  journal = {Agronomy},
  year = {2025},
  volume = {15},
  number = {4},
  pages = {796},
  doi = {10.3390/agronomy15040796}
}
Kostenlos starten →