YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards
To address the challenge of real-time kiwifruit detection in trellised orchards, this paper proposes YOLOv10-Kiwi, a lightweight detection model optimized for resource-constrained devices. First, a more compact network is developed by adjusting the scaling factors of the YOLOv10n architecture. Secon...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2025.1616165/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849225252963352576 |
|---|---|
| author | Jie Ren Wendong Wang Yuan Tian Jinrong He |
| author_facet | Jie Ren Wendong Wang Yuan Tian Jinrong He |
| author_sort | Jie Ren |
| collection | DOAJ |
| description | To address the challenge of real-time kiwifruit detection in trellised orchards, this paper proposes YOLOv10-Kiwi, a lightweight detection model optimized for resource-constrained devices. First, a more compact network is developed by adjusting the scaling factors of the YOLOv10n architecture. Second, to further reduce model complexity, a novel C2fDualHet module is proposed by integrating two consecutive Heterogeneous Kernel Convolution (HetConv) layers as a replacement for the traditional Bottleneck structure. This replacement enables parallel processing and enhances feature extraction efficiency. By combining heterogeneous kernels in sequence, C2fDualHet captures both local and global features while significantly lowering parameter count and computational cost. To mitigate potential accuracy loss due to lightweighting, a Cross-Channel Fusion Module (CCFM) is introduced in the neck network. This module incorporates four additional convolutional layers to adjust channel dimensions and strengthen cross-channel information flow, thereby enhancing multi-scale feature integration. In addition, a MPDIoU loss function is introduced to overcome the limitations of the traditional CIoU in terms of aspect ratio mismatch and bounding box regression, accelerating convergence and improving detection accuracy. Experimental results demonstrate that YOLOv10-Kiwi achieves a model size of only 2.02 MB, with 0.51M parameters and 2.1 GFLOPs, representing reductions of 80.34%, 81.11%, and 68.18%, respectively, compared to the YOLOv10n baseline. On a self-constructed kiwifruit dataset, the model achieves 93.6% mAP@50 and an inference speed of 74 FPS. YOLOv10-Kiwi offers an efficient solution for automated kiwifruit detection on low-power agricultural robots. |
| format | Article |
| id | doaj-art-5c77bccda079493685697e770c3759e0 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-5c77bccda079493685697e770c3759e02025-08-25T05:25:14ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-08-011610.3389/fpls.2025.16161651616165YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchardsJie RenWendong WangYuan TianJinrong HeTo address the challenge of real-time kiwifruit detection in trellised orchards, this paper proposes YOLOv10-Kiwi, a lightweight detection model optimized for resource-constrained devices. First, a more compact network is developed by adjusting the scaling factors of the YOLOv10n architecture. Second, to further reduce model complexity, a novel C2fDualHet module is proposed by integrating two consecutive Heterogeneous Kernel Convolution (HetConv) layers as a replacement for the traditional Bottleneck structure. This replacement enables parallel processing and enhances feature extraction efficiency. By combining heterogeneous kernels in sequence, C2fDualHet captures both local and global features while significantly lowering parameter count and computational cost. To mitigate potential accuracy loss due to lightweighting, a Cross-Channel Fusion Module (CCFM) is introduced in the neck network. This module incorporates four additional convolutional layers to adjust channel dimensions and strengthen cross-channel information flow, thereby enhancing multi-scale feature integration. In addition, a MPDIoU loss function is introduced to overcome the limitations of the traditional CIoU in terms of aspect ratio mismatch and bounding box regression, accelerating convergence and improving detection accuracy. Experimental results demonstrate that YOLOv10-Kiwi achieves a model size of only 2.02 MB, with 0.51M parameters and 2.1 GFLOPs, representing reductions of 80.34%, 81.11%, and 68.18%, respectively, compared to the YOLOv10n baseline. On a self-constructed kiwifruit dataset, the model achieves 93.6% mAP@50 and an inference speed of 74 FPS. YOLOv10-Kiwi offers an efficient solution for automated kiwifruit detection on low-power agricultural robots.https://www.frontiersin.org/articles/10.3389/fpls.2025.1616165/fullkiwifruit detectionYOLOv10lightweight networkHetConvCCFMMPDIou |
| spellingShingle | Jie Ren Wendong Wang Yuan Tian Jinrong He YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards Frontiers in Plant Science kiwifruit detection YOLOv10 lightweight network HetConv CCFM MPDIou |
| title | YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards |
| title_full | YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards |
| title_fullStr | YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards |
| title_full_unstemmed | YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards |
| title_short | YOLOv10-kiwi: a YOLOv10-based lightweight kiwifruit detection model in trellised orchards |
| title_sort | yolov10 kiwi a yolov10 based lightweight kiwifruit detection model in trellised orchards |
| topic | kiwifruit detection YOLOv10 lightweight network HetConv CCFM MPDIou |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1616165/full |
| work_keys_str_mv | AT jieren yolov10kiwiayolov10basedlightweightkiwifruitdetectionmodelintrellisedorchards AT wendongwang yolov10kiwiayolov10basedlightweightkiwifruitdetectionmodelintrellisedorchards AT yuantian yolov10kiwiayolov10basedlightweightkiwifruitdetectionmodelintrellisedorchards AT jinronghe yolov10kiwiayolov10basedlightweightkiwifruitdetectionmodelintrellisedorchards |