YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV
IntroductionDue to the limited computing power and fast flight speed of the picking of unmanned aerial vehicles (UAVs), it is important to design a quick and accurate detecting algorithm to obtain the fruit position.MethodsThis paper proposes a lightweight deep learning algorithm, named YOLOv8s-Long...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2024.1518294/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591694505181184 |
|---|---|
| author | Jun Li Jun Li Jun Li Kaixuan Wu Meiqi Zhang Hengxu Chen Hengyi Lin Yuju Mai Linlin Shi |
| author_facet | Jun Li Jun Li Jun Li Kaixuan Wu Meiqi Zhang Hengxu Chen Hengyi Lin Yuju Mai Linlin Shi |
| author_sort | Jun Li |
| collection | DOAJ |
| description | IntroductionDue to the limited computing power and fast flight speed of the picking of unmanned aerial vehicles (UAVs), it is important to design a quick and accurate detecting algorithm to obtain the fruit position.MethodsThis paper proposes a lightweight deep learning algorithm, named YOLOv8s-Longan, to improve the detection accuracy and reduce the number of model parameters for fruitpicking UAVs. To make the network lightweight and improve its generalization performance, the Average and Max pooling attention (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.Results and discussionThe 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 by 3.9% and reduces the number of parameters by 20.3%. It satisfies the high accuracy and fast detection requirements for fruit detection in fruit-picking UAV scenarios. |
| format | Article |
| id | doaj-art-4827953295fa4289a30854bae579ed80 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-4827953295fa4289a30854bae579ed802025-01-22T07:10:56ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-01-011510.3389/fpls.2024.15182941518294YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAVJun Li0Jun Li1Jun Li2Kaixuan Wu3Meiqi Zhang4Hengxu Chen5Hengyi Lin6Yuju Mai7Linlin Shi8College of Engineering, South China Agricultural University, Guangzhou, ChinaGuangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, ChinaState Key Laboratory of Agricultural Equipment Technology, Beijing, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaCollege of Engineering, South China Agricultural University, Guangzhou, ChinaIntroductionDue to the limited computing power and fast flight speed of the picking of unmanned aerial vehicles (UAVs), it is important to design a quick and accurate detecting algorithm to obtain the fruit position.MethodsThis paper proposes a lightweight deep learning algorithm, named YOLOv8s-Longan, to improve the detection accuracy and reduce the number of model parameters for fruitpicking UAVs. To make the network lightweight and improve its generalization performance, the Average and Max pooling attention (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.Results and discussionThe 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 by 3.9% and reduces the number of parameters by 20.3%. It satisfies the high accuracy and fast detection requirements for fruit detection in fruit-picking UAV scenarios.https://www.frontiersin.org/articles/10.3389/fpls.2024.1518294/fulllonganlightweight networkattention mechanismYOLOv8-Longan networktarget detection |
| spellingShingle | Jun Li Jun Li Jun Li Kaixuan Wu Meiqi Zhang Hengxu Chen Hengyi Lin Yuju Mai Linlin Shi YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV Frontiers in Plant Science longan lightweight network attention mechanism YOLOv8-Longan network target detection |
| title | YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV |
| title_full | YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV |
| title_fullStr | YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV |
| title_full_unstemmed | YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV |
| title_short | YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV |
| title_sort | yolov8s longan a lightweight detection method for the longan fruit picking uav |
| topic | longan lightweight network attention mechanism YOLOv8-Longan network target detection |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2024.1518294/full |
| work_keys_str_mv | AT junli yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT junli yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT junli yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT kaixuanwu yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT meiqizhang yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT hengxuchen yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT hengyilin yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT yujumai yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav AT linlinshi yolov8slonganalightweightdetectionmethodforthelonganfruitpickinguav |