Research on Insect‑bitten Zijin Tea Detection Method Based on YOLOv5s‑SE and Channel Pruning

doi:10.15933/j.cnki.1004-3268.2024.05.017

Journal of Henan Agricultural Sciences ›› 2024, Vol. 53 ›› Issue (5): 157-163.DOI: 10.15933/j.cnki.1004-3268.2024.05.017

• Agricultural Information and Engineering and Agricultural Product Processing • Previous Articles Next Articles

Research on Insect‑bitten Zijin Tea Detection Method Based on YOLOv5s‑SE and Channel Pruning

DAI Jiabing¹，SONG Chunfang¹，LING Caijin²，LI Zhenfeng¹，SUN Chonggao³

（1.College of Mechanical Engineering，Jiangnan University/Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment & Technology，Wuxi 214122，China；2.Tea Research Institute，Guangdong Academy of Agricultural Sciences/Guangdong Key Laboratory of Tea Plant Resources Innovation & Utilization，Guangzhou 510640，China；3.Shandong Bihai Packaging Materials Co.，Ltd.，Linyi 276600，China）

Received:2024-01-22 Published:2024-05-15 Online:2024-06-07

基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法研究

戴佳兵¹，宋春芳¹，凌彩金²，李臻锋¹，孙崇高³

（1.江南大学机械工程学院/江苏省食品先进制造装备技术重点实验室，江苏无锡 214122；2.广东省农业科学院茶叶研究所/广东省茶树资源创新利用重点实验室，广东广州 510640；3.山东碧海包装材料有限公司，山东临沂 276600）

通讯作者: 李臻锋（1968-），男，加拿大人，教授，博士，主要从事食品无损检测研究。E-mail：1736691239@qq.com
作者简介:戴佳兵（1997-），男，江苏泰兴人，在读硕士研究生，研究方向：计算机视觉及农业信息化。E-mail：1085769527@qq.com
基金资助:
以农产品为单元的广东省现代农业产业技术体系创新团队建设项目（茶叶）（2023KJ120）；河源市科技计划项目（河科2021030）；2024紫金县科技计划项目

Abstract

Abstract: In order to achieve rapid and accurate identification of insect‑bitten Zijin tea leaves in complex nature backgrounds，a detection method for Zijin tea based on YOLOv5s‑SE and channel pruning was proposed. Firstly,SE modules were added to the backbone network of YOLOv5s to enhance the model’s feature extraction capability and reduce interference from complex backgrounds during tea leaf feature extraction.Then,a channel pruning algorithm was used to prune the model and fine‑tuning was conducted,enabling fast and accurate detection of insect‑bitten Zijin tea leaves. Compared to YOLOv5s,the test results showed that the pruned model reduced parameters by 60.1%,improved FPS by 18.6%,reduced GFLOPs by 29.7%,and achieved mAP of 81.3%.

Key words: Tea, Object detection, Channel pruning, Attention mechanism, Deep learning

摘要： 为了实现复杂自然背景下虫咬紫金蝉茶的快速、准确识别，提出了一种基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法。首先在YOLOv5s的主干网络中添加SE注意力机制以增强模型特征提取的能力，降低复杂背景对茶叶特征提取时的干扰；然后采用通道剪枝算法对模型进行剪枝并进行微调，实现虫咬紫金蝉茶叶片的快速、准确检测。结果表明，修剪后的模型相比原YOLOv5s模型，参数量减少60.1%，帧率提升18.6%，运算量减少29.7%，平均精度均值（mAP）为81.3%。

关键词: 茶叶, 紫金蝉茶, 目标检测, 通道剪枝, 注意力机制, 深度学习

CLC Number:

DAI Jiabing, SONG Chunfang, LING Caijin, LI Zhenfeng, SUN Chonggao. Research on Insect‑bitten Zijin Tea Detection Method Based on YOLOv5s‑SE and Channel Pruning[J]. Journal of Henan Agricultural Sciences, 2024, 53(5): 157-163.

戴佳兵, 宋春芳, 凌彩金, 李臻锋, 孙崇高. 基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法研究[J]. 河南农业科学, 2024, 53(5): 157-163.

References

［1］MEI X，LIU X Y，ZHOU Y，et al. Formation and emission of linalool in tea（Camellia sinensis） leaves infested by tea green leafhopper（Empoasca（Matsumurasca）onukii Matsuda）［J］.Food Chemistry，2017，237：356‑363.

［2］ LIAO Y Y，YU Z M，LIU X Y，et al. Effect of major teainsect attack on formation of quality‑related nonvolatilespecialized metabolites in tea（Camellia sinensis）leaves［J］.Journal of Agricultural and Food Chemistry，2019，67（24）6716‑6724.

［3］李明金，朱艳宇，何春梅，等.小贯小绿叶蝉刺吸对青心大冇美人茶香气和滋味代谢物的影响［J］.食品科学， 2024，45（2）：248-257.

LI M J，ZHU Y Y，HE C M，et al. Effect of Empoasca onukii puncturing aroma- and taste-activate metabolites of qingxindamao beauty tea［J］. Food Science，2024，45（2）： 248-257.

［4］XU W K，ZHAO L G，LI J，et al. Detection and classification of tea buds based on deep learning［J］. Computers and Electronics in Agriculture，2022，192： 106547.

［5］SANDHU G K，KAUR R. Plant disease detection techniques：A review［C］//2019 International Conference on Automation， Computational and Technology Management（ICACTM）. London，UK：IEEE，2019： 34-38.

［6］ SUN Y Y，JIANG Z H，ZHANG L P，et al.SLIC_SVM based leaf diseases saliency map extraction of tea plant［J］.Computers and Electronics in Agriculture，2019， 157：102-109.

［7］HOSSAIN S，MOU R M，HASAN M M，et al.Recognition and detection of tea leaf's diseases using support vector machine［C］//2018 IEEE 14th International Colloquium on Signal Processing & Its Applications（CSPA）.Penang，Malaysia：IEEE，2018： 150-154.

［8］HU G S，WEI K，ZHANG Y，et al.Estimation of tea leaf blight severity in natural scene images［J］.Precision Agriculture，2021，22（4）：1239-1262.

［9］YANG J C，GUO X L，LI Y，et al. A survey of few-shot learning agriculture：Developments， applications，and challenges［J］.Plant Methods，2022，18 （1）：28.

［10］REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN： Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（6）：1137-1149.

［11］ RENDOM J，DIVVALA S，GIRSHICK R，et al. You only look once：Unified，real-time object detection［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Las Vegas，NV，USA： IEEE，2016：779-788. ［12］RENDOM J，FARHADI A. YOLO9000：better，faster， stronger［C］//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Honolulu，HI， USA：IEEE，2017：6517-6525.

［13］ RENDOM J，FARHADI A. YOLOv3：An incremental improvement［EB/OL］.（2018-04-08）［2023-10-20］. https：//doi.org/10.48550/arXiv.1804.02767.pdf.

［14］BOCHJOVSKIY A，WANG C Y，LIAO H Y M. YOLOv4：Optimal speed and accuracy of object detection［EB/OL］.（2020-04-23）［2023-10-20］.http：// arxiv. org/abs/2004. 10934. pdf.

［15］刘拥民，张炜，麻海志，等.基于注意力机制的轻量化 YOLO v5s蓝莓检测算法［J］.河南农业科学，2024，53 （3）：151-157.

LIU Y M，ZHANG W，MA H Z，et al. Lightweight YOLO v5s blueberry detection algorithm based on attention mechanism［J］. Journal of Henan Agricultural Sciences，2024，53（3）：151-157.

［16］ LIU W，ANGUELOV D，ERHAN D，et al. SSD：single shot MultiBox detector［C］//European Conference on Computer Vision. Cham：Springer，2016：21-37.

［17］ SUN X X，MU S M，XU Y Y，et al. Image recognition of tea leaf diseases based on convolutional neural network ［C］//2018 International Conference on Security，Pattern Analysis，and Cybernetics（SPAC）. Ji’nan，China：IEEE，2018：304-309.

［18］毛腾跃，朱俊杰，帖军.基于无锚框检测网络的茶叶嫩芽识别方法研究［J］.中南民族大学学报（自然科学版），2023，42（4）：489-496.

MAO T Y，ZHU J J，TIE J. Research based on recognition method for tea buds based on anchor free detection network［J］. Journal of South-Central Minzu University（Natural Science Edition），2023，42（4）： 489-496.

［19］ LI H，SHI H T，DU A H，et al. Symptom recognition of disease and insect damage based on Mask R-CNN， wavelet transform，and F-RNet［J］. Frontiers in Plant Science，2022，13：922797.

［20］ LEE S H，LIN S R，CHEN S F. Identification of tea foliar diseases and pest damage under practical field conditions using a convolutional neural network［J］. Plant Pathology，2020，69（9）：1731-1739.

［21］ HU J，SHEN L，SUN G. Squeeze-and-excitation networks ［C］//2018 IEEE/CVF Conference on Computer Vision ［22］江培营，陶青川，艾梦琴.基于注意力机制和深度学习的钢板表面缺陷图像分类［J］.计算机应用与软件， 2021，38（9）：214-219.

JIANG P Y，TAO Q C，AI M Q. Steel surface defect image classification based on attention mechanism and deep learning［J］.Computer Applications and Software， 2021，38（9）：214-219.

［23］ LIU Z，LI J G，SHEN Z Q，et al. Learning efficient convolutional networks through network slimming［C］// 2017 IEEE International Conference on Computer Vision（ICCV）.Venice，Italy：IEEE，2017：2755-2763.

［24］梁晓婷，庞琦，杨一，等.基于YOLOv4模型剪枝的番茄缺陷在线检测［J］.农业工程学报，2022，38（6）： 283-292.

LIANG X T，PANG Q，YANG Y，et al. Online detection of tomato defects based on YOLOv4 model pruning［J］. Transactions of the Chinese Society of Agricultural Engineering，2022，38（6）：283-292

[1]	HUANG Xiaolong, CHEN Zhongju, XU Haoran, LI Heping. Blurry Flower Image Detection Based on SR⁃YOLOv8n⁃BCG [J]. Journal of Henan Agricultural Sciences, 2024, 53(4): 161-171.
[2]	LI Dahua, KONG Shu, LI Dong, YU Xiao. Light Weight Detection Algorithm for Apple Surface Defect Based on Improved YOLOv7 [J]. Journal of Henan Agricultural Sciences, 2024, 53(3): 141-150.
[3]	LIU Yongmin, ZHANG Wei, MA Haizhi, LIU Yuan, ZHANG Yi. Lightweight YOLO v5s Blueberry Detection Algorithm Based on Attention Mechanism [J]. Journal of Henan Agricultural Sciences, 2024, 53(3): 151-157.
[4]	LI Dongya, BAT Tao, XIANG Huimin, DAI Shuo, WANG Zhenlu, CHEN Zhen. Recognition of Cotton Pests and Diseases Named Entities Based on RoBERTA Multi⁃feature Fusion [J]. Journal of Henan Agricultural Sciences, 2024, 53(2): 152-161.
[5]	YANG Chun, SU Shengfeng, YANG Daixing, LIANG Sihui, GUO Yan, GUO Can, CHEN Zhengwu. Comparison of Leaf Anatomical Atructure and Stress Resistance Analysis of Wild Tea Plants in Panzhou City and Sandu County，Guizhou Province [J]. Journal of Henan Agricultural Sciences, 2024, 53(1): 48-61.
[6]	YU Yannan, MO Yongbin, YAN Jichi, XIONG Chunlin, DOU Shiqing, YANG Rongfeng. Identification of Citrus Diseases Based on Improved ShuffleNet V2 [J]. Journal of Henan Agricultural Sciences, 2024, 53(1): 142-151.
[7]	ZHONG Zhengyang, YUN Lijun, YANG Xuanxi, CHEN Zaiqing. Research on Walnut Recognition Algorithm in Natural Environment Based on Improved YOLOX [J]. Journal of Henan Agricultural Sciences, 2024, 53(1): 152-161.
[8]	HAO Zirui, JIA Yuku, GE Zifei, BI Xintong, ZHANG Jian, XIE Yingxin, WANG Chenyang, MA Dongyun. Quality of Flour and Steamed Bread Made from Black Wheat [J]. Journal of Henan Agricultural Sciences, 2023, 52(8): 163-170.
[9]	ZHANG Liushuang, XIE Hui, YANG Jinqing, HAN Jiaqi, BAO Zhijuan. Effects of Tea Polyphenols on Physiological Indexes and Pb Accumulation in Tobacco under Pb Stress [J]. Journal of Henan Agricultural Sciences, 2023, 52(6): 34-40.
[10]	LI Yang, KANG Jungang, MA Zhanfei, WANG Yabo, ZHAO Bowei, JIANG Guojun. Effect of Traditional Chinese Medicine Residues On Growth Performance and Digestive Enzyme Activity of Earthworms [J]. Journal of Henan Agricultural Sciences, 2023, 52(5): 156-161.
[11]	LI Weihao, ZHAN Wei, ZHOU Wan, HAN Tao, WANG Peiwen, LIU Hu, XIONG Mengyuan, SUN Yong. Research and Application of Lightweight Yolov7‐TSA Network in Tea Disease Detection and Identification [J]. Journal of Henan Agricultural Sciences, 2023, 52(5): 162-169.
[12]	WANG Huanxin, SHEN Zhihao, LIU Quan, LIU Jinjiang. Identification of Crop Leaf Diseases Based on Improved MobileNetV2 Model [J]. Journal of Henan Agricultural Sciences, 2023, 52(4): 143-151.
[13]	CHEN Cong, YU Xiao, GONG Qi. Apple Leaf Diseases Identification Based on Improved Residual Network [J]. Journal of Henan Agricultural Sciences, 2023, 52(4): 152-161.
[14]	WEI Gaixing, YI Wenlong, LIU Yucheng, ZHAO Yingding, CHEN Tingzhuo. Research on Improved U‑Net Method for Rice Leaf Cell Segmentation [J]. Journal of Henan Agricultural Sciences, 2023, 52(3): 153-160.
[15]	ZANG Hecang, WANG Congsheng, ZHAO Qiaoli, ZHAO Qing, ZHANG Jie, LI Guoqiang, ZHENG Guoqing. Study on Automatic Classification Method of Wheat Lodging Based on Deep Learning [J]. Journal of Henan Agricultural Sciences, 2023, 52(11): 167-173.

Research on Insect‑bitten Zijin Tea Detection Method Based on YOLOv5s‑SE and Channel Pruning

基于YOLOv5s-SE和通道剪枝的虫咬紫金蝉茶检测方法研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics