Research on Improving YOLOv11n for Siraitia grosvenorii Pistil Detection Using SCConv and CoordAtt Dual-Module Synergy
Source abstract
Abstract
Precision-targeted pollination places strict demands on flower organ detection in field environments. In field conditions, pistil detection in Siraitia grosvenorii remains difficult because the targets are small, often occluded, and require accurate localization under lightweight model constraints. To address these challenges, we develop an improved YOLOv11n-based method for Siraitia grosvenorii pistil detection in precision pollination tasks. The model incorporates SCConv, CoordAtt, and SimAM to improve feature extraction and foreground discrimination for small pistil targets in complex backgrounds. The main contribution of this work lies in task-oriented module integration and lightweight optimization for tiny pistil detection, rather than in proposing a new generic detection operator. Experiments on the self-built dataset show that the improved model achieves 82.17% mAP@0.5, 40.38% mAP@0.5:0.95, and 86.20% precision, improving upon the YOLOv11n baseline by 2.92, 2.28, and 9.84 percentage points, respectively. Recall decreases from 78.46% to 76.50%, suggesting a precision-oriented trade-off in the current setting. With only 2.89 M parameters and 7.22 GFLOPs, the model maintains a lightweight architecture while achieving improved detection performance for targeted pollination tasks. These findings support the feasibility of the proposed method for Siraitia grosvenorii pistil detection in intelligent pollination applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Insect Pheromone Research and Control · Smart Agriculture and AI · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Control Engineering, Guilin University of Technology, Guilin 541004, China
Guangxi Institute of Botany, Chinese Academy of Sciences, Guilin 541006, China
Funding
Guilin Science and Technology Bureau
References (19)
Show source-provided references
1. Precision farming—The environmental challenge10.1016/S0168-1699(00)00153-8 ↗
2. Deep learning based approach for actinidia flower detection and gender assessment10.1038/s41598-024-73035-1 ↗
3. Wang, D., Song, H., and Wang, B. (2025). YO-AFD: An improved YOLOv8-based deep learning approach for rapid and accurate apple flower detection. Front. Plant Sci., 16.10.3389/fpls.2025.1541266 ↗
4. Wu, J., Xu, H., Zeng, J., Qi, Y.N., Yuan, Q.C., Huang, W.X., Ma, Z.B., Shen, Q.Y., and Lyu, X.L. (2022). A Review of the Phytochemistry and Pharmacology of the Fruit of Siraitia grosvenorii (Swingle): A Traditional Chinese Medicinal Food. Molecules, 27.10.3390/molecules27196618 ↗
5. Luohanguo yanjiu zongshu [A review of Siraitia grosvenorii research]
6. Real-time detection of kiwifruit flower and bud simultaneously in orchard using YOLOv4 for robotic pollination10.1016/j.compag.2021.106641 ↗
7. Vision-based fruit recognition and positioning technology for harvesting robots10.1016/j.compag.2023.108258 ↗
8. Zhang, S., Zhang, D., Zhang, J., Wang, J., Zhang, Y., Fan, X., and Zhou, Y. (2026). DSS-YOLO: A lightweight flower and stamen detection model for greenhouse tomato pollination assistance. Agronomy, 16.10.3390/agronomy16010067 ↗
9. Hou, Q., Zhou, D., and Feng, J. Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021, IEEE.10.1109/CVPR46437.2021.01350 ↗
10. Faster-YOLO-AP: A lightweight apple detection algorithm based on improved YOLOv8 with a new efficient PDWConv in orchard10.1016/j.compag.2024.109118 ↗
11. Effects of thinning flowers and fruits on the quality and benefit of Siraitia grosvenorii
12. (2019). Technical Regulations for Management of Siraitia grosvenorii during Flowering and Fruiting Stage (Standard No. DB45/T 1967-2019).
13. Monitoring of key Camellia oleifera phenology features using field cameras and deep learning10.1016/j.compag.2024.108748 ↗
14. Broussard, M.A., Coates, M., and Martinsen, P. (2023). Artificial Pollination Technologies: A Review. Agronomy, 13.10.3390/agronomy13051351 ↗
15. Research Progress in Mechanized and Intelligentized Pollination Technologies for Fruit and Vegetable Crops
16. Shape Classification Technology of Pollinated Tomato Flowers for Robotic Implementation10.1038/s41598-023-27971-z ↗
17. Duc Tai, N., Minh Trieu, N., and Truong Thinh, N. (2024). Modeling Positions and Orientations of Cantaloupe Flowers for Automatic Pollination. Agriculture, 14.10.3390/agriculture14050746 ↗
18. Li, J., Wen, Y., and He, L. SCConv: Spatial and channel reconstruction convolution for feature redundancy. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 18–22 June 2023, IEEE.10.1109/CVPR52729.2023.00596 ↗
19. Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18–24). SimAM: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the 38th International Conference on Machine Learning (ICML), Virtual Event.