EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLOv5-LiNet: A lightweight network for fruits instance segmentation

Olarewaju Mubashiru Lawal iD

PLOS ONE · 02.03.2023 · 18 (3) · e0282297

DOI: 10.1371/journal.pone.0282297 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 02.03.2023. Verfasst von Olarewaju Mubashiru Lawal. Beteiligte Einrichtung: Sanjiang Institute of Artificial Intelligence & Robotics, Yibin University, Sichuan, China. Hauptthemen laut MEDLINE: Fruit, Agriculture. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanxi Agricultural University Science and Technology Innovation Fund Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To meet the goals of computer vision-based understanding of images adopted in agriculture for improved fruit production, it is expected of a recognition model to be robust against complex and changeable environment, fast, accurate and lightweight for a low power computing platform deployment. For this reason, a lightweight YOLOv5-LiNet model for fruit instance segmentation to strengthen fruit detection was proposed based on the modified YOLOv5n. The model included Stem, Shuffle_Block, ResNet and SPPF as backbone network, PANet as neck network, and EIoU loss function to enhance detection performance. YOLOv5-LiNet was compared to YOLOv5n, YOLOv5-GhostNet, YOLOv5-MobileNetv3, YOLOv5-LiNetBiFPN, YOLOv5-LiNetC, YOLOv5-LiNet, YOLOv5-LiNetFPN, YOLOv5-Efficientlite, YOLOv4-tiny and YOLOv5-ShuffleNetv2 lightweight model including Mask-RCNN. The obtained results show that YOLOv5-LiNet having the box accuracy of 0.893, instance segmentation accuracy of 0.885, weight size of 3.0 MB and real-time detection of 2.6 ms combined together outperformed other lightweight models. Therefore, the YOLOv5-LiNet model is robust, accurate, fast, applicable to low power computing devices and extendable to other agricultural products for instance segmentation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FruitAgricultureDendritic SpinesNeckRecognition, Psychology

Autor:innen und Institutionen

  • Sanjiang Institute of Artificial Intelligence & Robotics, Yibin University, Sichuan, China.

ORCID-Profile: Olarewaju Mubashiru Lawal

Förderung

  • Shanxi Agricultural University Science and Technology Innovation Fund Project

Zitieren

APA

Lawal, O. M. (2023). YOLOv5-LiNet: A lightweight network for fruits instance segmentation. PLOS ONE, 18(3), e0282297. https://doi.org/10.1371/journal.pone.0282297

Vancouver

Lawal OM. YOLOv5-LiNet: A lightweight network for fruits instance segmentation. PLOS ONE. 2023;18(3):e0282297. doi:10.1371/journal.pone.0282297

BibTeX
@article{Lawal2023,
  author = {Lawal, Olarewaju Mubashiru},
  title = {YOLOv5-LiNet: A lightweight network for fruits instance segmentation},
  journal = {PLOS ONE},
  year = {2023},
  volume = {18},
  number = {3},
  pages = {e0282297},
  doi = {10.1371/journal.pone.0282297}
}
Kostenlos starten →