YOLOv8-Based Recognition of Wolfberry Pistil Assisted Pollination

DOI: https://doi.org/10.62517/jlsa.202507107

Author(s)

Junlong Hou, Ziyou Chen, Yan Cao, Haiyang Wang*, Shuai Yan

Affiliation(s)

School of Computer Science and Engineering, North Minzu University, Yinchuan, Ningxia, China *Corresponding Author.

Abstract

In this paper, a pistil-assisted pollination recognition method based on improved YOLOv8 is proposed, aiming to improve the detection accuracy and efficiency in the pistil pollination process. Firstly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to replace the PAN-FPN module in YOLOv8 to enhance the multi-scale feature fusion capability for the complex background and small target features of pistil images. Secondly, the Coordinate Attention (CA) mechanism is combined to further enhance the extraction ability of the model for stamen features. In addition, Ghost convolution is used to replace the traditional convolution, which effectively reduces the computational complexity and storage requirements of the model. The experimental results show that the improved YOLOv8 model achieves a mean average precision (mAP) of 90.5% on the self-constructed stamen dataset. The method provides an efficient and accurate solution for pistil-assisted pollination identification, which is suitable for real-time detection and low-match device deployment.

Keywords

Agricultural Decision Support; Mechanised Pollination; Image Classification; YOLOv8; Data Enhancement

References

[1]Li Chunhui, Lyu Yan, Meng Xianglai, et al. Intelligent Defect Recognition Technology for Magnetic Flux Leakage Detection in Oil and Gas Pipelines Based on YOLOv8. Chinese Journal of Scientific Instrument, 1-8[2025-03-25]. https:// doi.org/ 10.19650/ j.cnki.cjsi.J2413188. [2]Pi Daneng, Zhou Qi, Yang Yiqun, et al. Research on a Water Surface Garbage Detection Model Based on Improved YOLOv8. Journal of Hubei Normal University (Natural Science Edition), 2025, 45(01): 27-34. [3]Wu Yuhao, Zhu Wenzhong, Luo Yuan, et al. Substation Defect Detection Algorithm Based on Improved YOLOv8. Journal of Sichuan University of Science & Engineering (Natural Science Edition), 1-12[2025-03-25]. [4]Zhang Shuai, Wang Botao, Tu Jiayi, et al. SCE-YOLO: A Lightweight UAV Visual Detection Algorithm Based on Improved YOLOv8. Computer Engineering and Applications, 1-14[2025-03-25]. [5]Yan Yujing, Hou Xia, Guo Yuting, et al. A Medical Visual Question Answering Network with Dual Data-Knowledge Enhancement. Computer Science, 1-13[2025-03-25]. http: //kns. cnki. net/ kcms/detail/ 50.1075. TP.20250317. 1543. 020. html. [6]Xiao Litong, Wang Xi. Weed Detection Model in Corn Fields Based on Improved YOLO Algorithm. Journal of Agricultural Mechanization Research, 2025, 47(08): 10-16. DOI:10. 13427/j. issn. 1003-188X.2025. 08.002. [7]Chen Si, Li Junqiu, Kong Dexiao, et al. Research on Green Orange Detection Algorithm Based on YOLOv8n. Journal of Chinese Agricultural Mechanization, 1-8[2025-03-25]. http:// kns.cnki.net/ kcms /detail/32. 1837.S. 20250319.1719.002. html. [8]Sun Yueyue. Synergistic Applications of Big Data and AI in Agriculture. Agricultural Technology & Equipment, 2024, (07): 8-10. [9]Ren Jiayu. Research on Intelligent Management Decision Support System in Precision Agriculture. Agricultural Machinery Use & Maintenance, 2023, (04): 93-95. DOI: 10.14031/j. cnki.njwx. 2023.04. 029. [10]Zhong Boping. Design and Experiment of an Airflow-Assisted High-Clearance Hybrid Rice Pollination Machine. South China Agricultural University, 2019. DOI: 10.27152/d. cnki. ghanu.2019.001133. [11]Zhu Dingyun, Chen Yiyao. Fire Image Classification Method Based on Improved YOLOv8. Journal of Shanghai Polytechnic University, 1-7[2025-03-25]. http:// kns.cnki. net/kcms/detail/31.1496.t.20250314.1630.014.html. [12]Liu Qi, Dai Dongnan, Sun Mengyan, et al. Surface Defect Recognition of Cherry Tomatoes Based on Dual Attention Fusion Network. Journal of Chinese Agricultural Mechanization, 2025, 46(03): 153-159. DOI:10.13733/j.jcam.issn.2095-5553. 2025. 03. 023. [13]Xu Wenqing, Ding Aixia, Zhu Wenqing. Advances in Fruit Grading Detection Based on Digital Image Processing Technology. China Food Safety Magazine, 2025, (04): 183-189. DOI: 10.16043/j. cnki.cfs. 2025.04. 045.