基于改进的YOLOv8草莓成熟度检测算法研究
Research on Strawberry Maturity Detection Algorithm Based on Improved YOLOv8
DOI: 10.12677/jsta.2025.136091, PDF,    科研立项经费支持
作者: 李柟莹, 赖成果, 曾晏林*:重庆对外经贸学院大数据与智能工程学院,重庆
关键词: YOLOv8草莓成熟度检测注意力机制CBAM轻量化网络YOLOv8 Strawberry Maturity Detection CBAM Attention Mechanism Lightweight Network
摘要: 为克服传统草莓成熟度识别方式的效率与准确性局限,本研究开发了一种高效、精准且结构轻量的自动化检测模型,以促进智慧农业在草莓生产中的应用。本研究设计了一种基于改进YOLOv8框架的轻量化识别系统。该系统以YOLOv8s为基础,在主干网络末端引入通道–空间双路注意力机制(CBAM),通过自适应权重分配增强对草莓果面光泽和种子色泽等关键性状的感知能力。同时,将原C2f模块替换为FasterNet中的C2f_Faster轻量型结构,从而在维持特征提取性能的前提下精简模型参数。优化模型在草莓成熟度判别任务中表现优异。最终检测精度达97.2%,较原YOLOv8s模型提升0.8个百分点。模型参数量减少16.2%,计算量降低32.7%,实现了轻量化目标。在遮挡场景下,小目标检测精度提升0.3个百分点。该方法可快速准确检测温室环境下的草莓果实成熟度,在精度和效率上均优于原模型,为草莓种植中的智慧农业应用提供有效技术解决方案。
Abstract: To address the limitations of conventional strawberry maturity assessment methods in terms of efficiency and accuracy, this study develops an automated detection model that is efficient, precise, and structurally lightweight, thereby facilitating the application of smart agriculture in strawberry production. A lightweight recognition system based on an improved YOLOv8 framework was designed. Using YOLOv8s as the base architecture, a Channel and Spatial Dual-Path Attention Mechanism (CBAM) was introduced at the end of the backbone network, enhancing perception of key traits such as fruit surface gloss and seed coloration through adaptive weight allocation. Simultaneously, the original C2f module was replaced with the C2f_Faster lightweight structure from FasterNet, thereby reducing model parameters while maintaining feature extraction performance. The optimized model performed excellently in strawberry maturity discrimination tasks. The final detection accuracy reached 97.2%, an improvement of 0.8 percentage points over the original YOLOv8s model. The parameter count was reduced by 16.2%, and computational load decreased by 32.7%, achieving lightweight objectives. In occluded scenarios, small target detection accuracy improved by 0.3 percentage points. This method enables rapid and accurate detection of strawberry fruit maturity in greenhouse environments, outperforming the original model in both accuracy and efficiency, and provides an effective technical solution for smart agriculture applications in strawberry cultivation.
文章引用:李柟莹, 赖成果, 曾晏林. 基于改进的YOLOv8草莓成熟度检测算法研究[J]. 传感器技术与应用, 2025, 13(6): 934-944. https://doi.org/10.12677/jsta.2025.136091

参考文献

[1] 周明源, 徐明泽, 田炜玮, 等. 不同类型草莓栽培模式优缺点分析[J]. 农业工程技术, 2023, 43(3): 63-65, 68.
[2] 刘畅, 王晓, 李宪松, 等. 我国草莓生产态势及国内外比较分析[J]. 中国果树, 2023(7): 136-140.
[3] Xiong, Y., From, P.J. and Isler, V. (2018) Design and Evaluation of a Novel Cable-Driven Gripper with Perception Capabilities for Strawberry Picking Robots. 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, 21-25 May 2018, 7384-7391. [Google Scholar] [CrossRef
[4] 孙兴民, 陈巍, 吕慧. 南京市草莓生产成本和综合收益研究[J]. 中国果业信息, 2020, 37(8): 26-28, 31.
[5] 刘晓敏, 田德宝, 宋懋征, 等. 气动球果采摘柔性手爪设计与实验[J]. 农业机械学报, 2021, 52(2): 30-43.
[6] 徐铭辰, 牛媛媛, 余永昌. 果蔬采摘机器人研究综述[J]. 安徽农业科学, 2014, 42(31): 11024-11027, 11057.
[7] Zhou, C., Hu, J., Xu, Z., Yue, J., Ye, H. and Yang, G. (2020) A Novel Greenhouse-Based System for the Detection and Plumpness Assessment of Strawberry Using an Improved Deep Learning Technique. Frontiers in Plant Science, 11, Article 559. [Google Scholar] [CrossRef] [PubMed]
[8] Irie, N., Taguchi, N., Horie, T. and Ishimatsu, T. (2009) Asparagus Harvesting Robot Coordinated with 3-D Vision Sensor. 2009 IEEE International Conference on Industrial Technology, Churchill, 10-13 February 2009, 1-6. [Google Scholar] [CrossRef
[9] Kennedy, G., Ila, V. and Mahony, R. (2019) A Perception Pipeline for Robotic Harvesting of Green Asparagus. IFAC-PapersOnLine, 52, 288-293. [Google Scholar] [CrossRef
[10] Sakai, H., Shiigi, T., Kondo, N., Ogawa, Y. and Taguchi, N. (2013) Accurate Position Detecting during Asparagus Spear Harvesting Using a Laser Sensor. Engineering in Agriculture, Environment and Food, 6, 105-110. [Google Scholar] [CrossRef
[11] Ivanova, J., Kampe, H., Liu, X. and Gräser, A. (2017) Vision Based Recognition and Tracking of Green Asparagus in Ambient Light. AtAutomatisierungstechnik, 65, 280-292. [Google Scholar] [CrossRef
[12] Leu, A., Razavi, M., Langstadtler, L., Ristic-Durrant, D., Raffel, H., Schenck, C., et al. (2017) Robotic Green Asparagus Selective Harvesting. IEEE/ASME Transactions on Mechatronics, 22, 2401-2410. [Google Scholar] [CrossRef
[13] 易杰, 单以才. 基于YOLOv10-IAS的草莓各个发育阶段成熟度检测模型[J/OL]. 南京农业大学学报: 1-13.
https://link.cnki.net/urlid/32.1148.S.20241223.1025.002, 2025-09-12.
[14] 李红丹. 基于深度学习的草莓果实成熟度检测研究[D]: [硕士学位论文]. 雅安: 四川农业大学, 2024.
[15] 李佳俊, 朱子峰, 刘洪鑫, 等. 基于改进FasterR-CNN模型的草莓果实识别算法[J]. 湖北农业科学, 2023, 62(11): 183-190.
[16] 杨滨硕, 狄巨星, 杨阳. YOLOv8-DG: 基于YOLOv8s改进的草莓成熟度检测模型[J]. 长江信息通信, 2025, 38(1): 82-86.
[17] 刘苏杭, 张华, 朱婷倩, 等. 基于改进YOLOv5的草莓病害及养分状况识别与检测[J]. 安徽科技学院学报, 2024, 38(2): 87-94.
[18] 姜业帆, 江朝晖, 朱瑞, 等. 基于PCIA-YOLO的复杂环境下草莓成熟度轻量化检测方法[J/OL]. 南京农业大学学报: 1-15.
https://link.cnki.net/urlid/32.1148.S.20240930.1738.008, 2025-09-12.
[19] Lemsalu, M., Bloch, V., Backman, J. and Pastell, M. (2022) Real-Time CNN-Based Computer Vision System for Open-Field Strawberry Harvesting Robot. IFAC-PapersOnLine, 55, 24-29. [Google Scholar] [CrossRef
[20] Raj, R., Cosgun, A. and Kulić, D. (2022) Strawberry Water Content Estimation and Ripeness Classification Using Hyperspectral Sensing. Agronomy, 12, Article 425. [Google Scholar] [CrossRef
[21] Ünal, İ. and Eceoğlu, O. (2025) A Lightweight Instance Segmentation Model for Simultaneous Detection of Citrus Fruit Ripeness and Red Scale (Aonidiella aurantii) Pest Damage. Applied Sciences, 15, Article 9742. [Google Scholar] [CrossRef
[22] Liang, C., Liu, D., Ge, W., Huang, W., Lan, Y. and Long, Y. (2025) Detection of Litchi Fruit Maturity States Based on Unmanned Aerial Vehicle Remote Sensing and Improved YOLOv8 Model. Frontiers in Plant Science, 16, Article 1568237. [Google Scholar] [CrossRef] [PubMed]
[23] Ultralytics (2023) YOLOv8 2023.
https://github.com/ultralytics/ultralytics
[24] Woo, S., Park, J., Lee, J. and Kweon, I.S. (2018) CBAM: Convolutional Block Attention Module. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer VisionECCV 2018, Springer, 3-19. [Google Scholar] [CrossRef
[25] Chen, J., Kao, S., He, H., Zhuo, W., Wen, S., Lee, C., et al. (2023) Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 12021-12031. [Google Scholar] [CrossRef