EUVIMEDEUVIMED entdecken
Crossref

Comparative Evaluation of YOLO-Based Pretrained Models for Multi-Class Vegetable Detection

Sakibul Chowdhury, Yakup Kutlu, Nalanda Goongoon

Tethys Environmental Science · 2026

DOI: 10.71350/tethysjournal.2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tethys Environmental Science, 2026. Verfasst von Sakibul Chowdhury und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate detection of vegetables from images is an essential task in precision agriculture, automated food supply chains and smart retail systems.Even with a little labeled data, recent developments in deep learning, especially pretrained object detection models, have greatly enhanced performance on visual recognition tasks.However, the relative effectiveness of modern pretrained object detection architectures on agricultural datasets remains underexplored.In this study, we present a comprehensive comparative evaluation of multiple state-of-the-art pretrained object detection models on a publicly available vegetable object detection dataset from Bangladesh.The evaluated models include RF-DETR (Large), YOLOv11 variants, Roboflow 3.0 Object Detection models and YOLOv12 variants with different capacity configurations (Fast, Accurate and Extra Large).Standard metrics like recall, precision and mAP@50 on a predetermined test set are used to evaluate performance.Experimental results demonstrate that YOLOv12 (Extra Large) significantly outperforms other models, achieving an mAP@50 of 79.0%, precision of 81.8% and recall of 80.7%.When implementing pretrained detectors in agricultural computer vision applications, the results emphasize the significance of model architecture and scale.

Zitieren

APA

Chowdhury, S., Kutlu, Y., & Goongoon, N. (2026). Comparative Evaluation of YOLO-Based Pretrained Models for Multi-Class Vegetable Detection. Tethys Environmental Science. https://doi.org/10.71350/tethysjournal.2

Vancouver

Chowdhury S, Kutlu Y, Goongoon N. Comparative Evaluation of YOLO-Based Pretrained Models for Multi-Class Vegetable Detection. Tethys Environmental Science. 2026. doi:10.71350/tethysjournal.2

BibTeX
@article{Chowdhury2026,
  author = {Chowdhury, Sakibul and Kutlu, Yakup and Goongoon, Nalanda},
  title = {Comparative Evaluation of YOLO-Based Pretrained Models for Multi-Class Vegetable Detection},
  journal = {Tethys Environmental Science},
  year = {2026},
  doi = {10.71350/tethysjournal.2}
}
Kostenlos starten →