Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Technical Advances in Plant Science
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1518294
This article is part of the Research Topic Optimizing Deep Learning for Effective Plant Species Recognition and Conservation View all 9 articles

YOLOv8s-Longan: A lightweight detection method for the Longan fruit-picking UAV

Provisionally accepted
JUN LI JUN LI 1,2,3Kaixuan Wu Kaixuan Wu 1Meiqi Zhang Meiqi Zhang 1Hengxu Chen Hengxu Chen 1Hengyi Lin Hengyi Lin 1Yuju Mai Yuju Mai 1Linlin Shi Linlin Shi 1*
  • 1 College of Engineering, South China Agricultural University, Guangzhou, China
  • 2 Guangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, China
  • 3 State Key Laboratory of Agricultural Equipment Technology, Beijing, China

The final, formatted version of the article will be published soon.

    Due to the limited computing power and fast flight speed of the picking unmanned aerial vehicle (UAV), it is important to design a quick and accurate detecting algorithm to obtain the fruit position.Therefore, this paper proposes a lightweight deep learning algorithm, named YOLOv8s-Longan to improve the detection accuracy and reduce the number of model parameters for the picking-UAV.To make the network lightweight and improve its generalization performance, the AMA attention module is designed and integrated into the DenseAMA and C2f-Faster-AMA modules on the proposed backbone network. To improve the detection accuracy, a crossstage local network structure VOVGSCSPC module is designed, which can help the model better understand the information of the image through multiscale feature fusion and improve the perception and expression ability of the model. Meanwhile, the novel Inner-SIoU loss function is proposed as the loss function of the target bounding box. The experimental results show that the proposed algorithm has good detection ability for densely distributed and mutually occluded longan string fruit under complex backgrounds with a mAP@0.5 of 84.3%. Compared with other YOLOv8 models, the improved model of mAP@0.5 improves 3.9% and reduces the amount of parameters by 20.3%. It satisfies the high accuracy and fast detection requirements for fruit detection in fruit-picking UAV scenarios.

    Keywords: Longan, Lightweight Network, attention mechanism, YOLOv8-Longan network, target detection

    Received: 28 Oct 2024; Accepted: 31 Dec 2024.

    Copyright: © 2024 LI, Wu, Zhang, Chen, Lin, Mai and Shi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Linlin Shi, College of Engineering, South China Agricultural University, Guangzhou, 510642, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.