EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A lightweight YOLO-TinyFuse model for small target detection of olive fruits

Xinyu Yang, Yichun Lin, Qiwen Xiao, Ziyao Liang, Luyao Ma, Yaxi ShuoGuo, Kugu Ade, Zhaoguo Tong, Yu Chen, Ying Cao

Frontiers in Plant Science · 24.02.2026 · 17

DOI: 10.3389/fpls.2026.1773377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 24.02.2026. Verfasst von Xinyu Yang und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Sichuan Agricultural University, Ya'an, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In response to the challenges posed by the large number of small targets, complex backgrounds and significant computational load involved in detecting olives, this study presents YOLO-TinyFuse, a lightweight detection model developed based on YOLOv8n. This model incorporates the P2 high-resolution feature layer, a ModifiedNeck cross-scale fusion structure (ModifiedNeck) and a bidirectional feature pyramid network (BiFPN) dynamic weighting module within a unified architecture. This architecture simultaneously preserves high-resolution feature representations, enhances bidirectional multi-scale interaction and optimises weighted feature aggregation. This synergistic design substantially improves the recognition of small objects while reducing model complexity further. Evaluations conducted on a multi-scenario olive phenotyping dataset demonstrate that YOLO-TinyFuse achieves an mAP50 of 92.3% and a Recall of 84.5%. This represents improvements of 2.6% and 3.2% respectively over YOLOv8n, while reducing the parameter count by 6.76%. These results confirm that the proposed model provides a deployable, computationally efficient, real-time solution for target recognition on mainstream edge computing platforms in automated olive harvesting scenarios, and offers a reusable, lightweight framework for agricultural small-object detection tasks requiring high performance and optimised computational efficiency.

Schlagwörter

Stichwörter der Autor:innen

BiFPNModifiedNeckOlea europaeaP2 layerYOLOv8lightweight model designsmall object detection

Autor:innen und Institutionen

  • College of Information Engineering, Sichuan Agricultural University, Ya'an, China.
  • College of Food Science, Sichuan Agricultural University, Ya'an, China.
  • College of Water Conservancy and Hydropower Engineering, Sichuan Agricultural University, Ya'an, China.
  • Panxi Crop Improvement Key Laboratory of Sichuan Province, Xichang University, Xichang, Sichuan, China.
  • School of Arts and Media, Sichuan Agricultural University, Ya'an, China.

Zitieren

APA

Yang, X., Lin, Y., Xiao, Q., Liang, Z., Ma, L., ShuoGuo, Y., Ade, K., Tong, Z., Chen, Y., & Cao, Y. (2026). A lightweight YOLO-TinyFuse model for small target detection of olive fruits. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1773377

Vancouver

Yang X, Lin Y, Xiao Q, Liang Z, Ma L, ShuoGuo Y, et al. A lightweight YOLO-TinyFuse model for small target detection of olive fruits. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1773377

BibTeX
@article{Yang2026,
  author = {Yang, Xinyu and Lin, Yichun and Xiao, Qiwen and Liang, Ziyao and Ma, Luyao and ShuoGuo, Yaxi and Ade, Kugu and Tong, Zhaoguo and Chen, Yu and Cao, Ying},
  title = {A lightweight YOLO-TinyFuse model for small target detection of olive fruits},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1773377}
}
Kostenlos starten →