[1]杨宏宇,谢小龙,郭容,等.基于EBS-YOLO v7的轻量化葡萄病害识别方法[J].江苏农业科学,2025,53(5):165-174.
 Yang Hongyu,et al.Lightweight grape disease recognition method based on EBS-YOLO v7[J].Jiangsu Agricultural Sciences,2025,53(5):165-174.
点击复制

基于EBS-YOLO v7的轻量化葡萄病害识别方法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第53卷
期数:
2025年第5期
页码:
165-174
栏目:
病害智能检测
出版日期:
2025-03-05

文章信息/Info

Title:
Lightweight grape disease recognition method based on EBS-YOLO v7
作者:
杨宏宇1谢小龙2郭容2张佳进2
1.云南农业大学机电工程学院,云南昆明 650201; 2.云南农业大学大数据学院,云南昆明 650201
Author(s):
Yang Hongyuet al
关键词:
目标检测病害识别轻量化YOLO v7注意力机制SIoU
Keywords:
-
分类号:
TP391.41;S126
DOI:
-
文献标志码:
A
摘要:
为了解决葡萄病害检测过程中存在的识别精度低、模型计算复杂度高及参数量大等问题,提出一种基于EBS- YOLO v7的轻量化葡萄病害识别方法。该方法使用EfficientNet轻量化网络结构替换YOLO v7主干网络,使模型在降低计算量及参数量的同时保持检测精度;在主干网络不同尺度特征输出层嵌入BiFormer注意力机制,强化模型对病害区域特征的提取能力,提高对细节、全局信息的理解能力;采用 SIoU(SCYLLA 交并比)损失函数作为边界框损失函数,加快模型收敛速度并提高边界框预测精度。结果表明,EBS- YOLO v7模型的准确率、召回率、平均精度均值分别达到97.4%、96.2%、98.3%,相较于YOLO v7模型分别提高了2.4、2.3、2.8百分点,参数量、计算量分别减少至原模型的32.5%、20.0%。与SSD、Faster-RCNN、YOLO v5模型相比,改进模型的平均精度均值分别提高6.0、119、7.2百分点,且参数量、计算量也均低于其他模型。研究结果显示,EBS-YOLO v7模型在保持高检测精度的同时,大幅降低了计算资源的消耗,可为葡萄病害的精准快速识别提供技术支持。
Abstract:
-

参考文献/References:

[1]Chen Y P,Wu Q F. Grape leaf disease identification with sparse data via generative adversarial networks and convolutional neural networks[J]. Precision Agriculture,2023,24(1):235-253.
[2]蔡易南,肖小玲. 基于改进YOLO v5n的葡萄叶病虫害检测模型轻量化方法[J]. 江苏农业科学,2024,52(7):198-205.
[3]张林鍹,巴音塔娜,曾庆松. 基于StyleGAN2-ADA和改进YOLO v7的葡萄叶片早期病害检测方法[J]. 农业机械学报,2024,55(1):241-252.
[4]Astani M,Hasheminejad M,Vaghefi M. A diverse ensemble classifier for tomato disease recognition[J]. Computers and Electronics in Agriculture,2022,198:107054.
[5]董雁凯,王玉超,李博梾,等. 基于改进YOLO v5的黄瓜霜霉病分级方法[J]. 江苏农业科学,2023,51(22):213-220.
[6]Javidan S M,Banakar A,Vakilian K A,et al. Diagnosis of grape leaf diseases using automatic K-means clustering and machine learning[J]. Smart Agricultural Technology,2023,3:100081.
[7]Khan H,Haq I U,Munsif M,et al. Automated wheat diseases classification framework using advanced machine learning technique[J]. Agriculture,2022,12(8):1226.
[8]Aggarwal M,Khullar V,Goyal N,et al. Pre-trained deep neural network-based features selection supported machine learning for rice leaf disease classification[J]. Agriculture,2023,13(5):936.
[9]袁培森,曹益飞,马千里,等. 基于Random Forest的水稻细菌性条斑病识别方法研究[J]. 农业机械学报,2021,52(1):139-145,208.
[10]Pan J C,Wang T Y,Wu Q F. RiceNet:a two stage machine learning method for rice disease identification[J]. Biosystems Engineering,2023,225:25-40.
[11]Xu L X,Cao B X,Zhao F J,et al. Wheat leaf disease identification based on deep learning algorithms[J]. Physiological and Molecular Plant Pathology,2023,123:101940.
[12]肖天赐,陈燕红,李永可,等. 基于改进通道注意力机制的农作物病害识别模型研究[J]. 江苏农业科学,2023,51(24):168-175.
[13]Alsubai S,Dutta A K,Alkhayyat A H,et al. Hybrid deep learning with improved Salp swarm optimization based multi-class grape disease classification model[J]. Computers and Electrical Engineering,2023,108:108733.
[14]贾璐,叶中华. 基于注意力机制和特征融合的葡萄病害识别模型[J]. 农业机械学报,2023,54(7):223-233.
[15]樊湘鹏,许燕,周建平,等. 基于迁移学习和改进CNN的葡萄叶部病害检测系统[J]. 农业工程学报,2021,37(6):151-159.
[16]Chen W R,Chen J D,Duan R,et al. MS-DNet:a mobile neural network for plant disease identification[J]. Computers and Electronics in Agriculture,2022,199:107175.
[17]毛锐,张宇晨,王泽玺,等. 利用改进Faster-RCNN识别小麦条锈病和黄矮病[J]. 农业工程学报,2022,38(17):176-185.
[18]徐艳蕾,孔朔琳,陈清源,等. 基于Transformer的强泛化苹果叶片病害识别模型[J]. 农业工程学报,2022,38(16):198-206.
[19]方逵,李成,何潇,等. 基于三维重建的多角度葡萄叶病害识别方法研究[J]. 中国农业科技导报,2022,24(7):86-96.
[20]Yuan Y,Chen L. An image dataset for IDADP-grape disease identification[J]. China Scientific Data,2022,7(1):86-90.
[21]Chen J C,Ma B X,Ji C,et al. Apple inflorescence recognition of phenology stage in complex background based on improved YOLO v7[J]. Computers and Electronics in Agriculture,2023,211:108048.
[22]刘诗怡,胡滨,赵春. 基于改进YOLO v7的黄瓜叶片病虫害检测与识别[J]. 农业工程学报,2023,39(15):163-171.
[23]Chen W B,Liu M C,Zhao C J,et al. MTD-YOLO:multi-task deep convolutional neural network for cherry tomato fruit bunch maturity detection[J]. Computers and Electronics in Agriculture,2024,216:108533.
[24]范天浩,顾寄南,王文波,等. 基于改进YOLO v5s的轻量化金银花识别方法[J]. 农业工程学报,2023,39(11):192-200.
[25]王瑞鹏,陈锋军,朱学岩,等. 采用改进的EfficientNet识别苹果叶片病害[J]. 农业工程学报,2023,39(18):201-210.
[26]Zhu L,Wang X J,Ke Z H,et al. BiFormer:vision transformer with bi-level routing attention[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver,BC,Canada:IEEE,2023:10323-10333.
[27]贾岚,徐雪环,罗德弢,等. 基于改进YOLO v7-tiny的跨阶段作物害虫检测[J/OL]. 南京农业大学学报,2024:1-13(2024-06-25)[2024-07-01]. https://kns.cnki.net/kcms2/article/abstract?v=_bj0XFJq-763ydghG8UiPVRchkPM 5vGFzTOqz1rLcYDJ0_NOoC5Jip3NSkR Fwsfjr520Uksuml6DpDUlD 5WwNCDSOxjqr2tvZTkwaFR1UvkG4XRAPyKN37EdvpNAeXHTNc lVKlqzISxjRzU- d9ifQQzo8pEpkkG_8jFZ0hSFLPIMiTwMYEbq3 PKk7OLaZP-0&uniplatform=NZKPT&language=CHS.
[28]Gevorgyan Z. SIoU loss:more powerful learning for bounding box regression[EB/OL]. (2022-05-25)[2024-07-01]. https://arxiv.org/abs/2205.12740v1.

相似文献/References:

[1]徐凯宏,米雅婷,谷志新.基于GA-BP神经网络的温室番茄病害诊断[J].江苏农业科学,2016,44(04):387.
 Xu Kaihong,et al.Diagnosis of tomato disease in greenhouse based on GA-BP network[J].Jiangsu Agricultural Sciences,2016,44(5):387.
[2]张会敏,张云龙,张善文,等.基于区分矩阵的属性约简算法的作物病害识别方法[J].江苏农业科学,2015,43(01):387.
 Zhang Huimin,et al.A crop disease recognition method based on attribute reduction of discernibility matrix[J].Jiangsu Agricultural Sciences,2015,43(5):387.
[3]张云龙,袁浩,张晴晴,等.基于颜色特征和差直方图的苹果叶部病害识别方法[J].江苏农业科学,2017,45(14):171.
 Zhang Yunlong,et al.Apple leaf disease recognition based on color characteristics and differential histogram[J].Jiangsu Agricultural Sciences,2017,45(5):171.
[4]刁智华,刁春迎,魏玉泉,等.机器人系统中小麦病害识别与施药算法研究[J].江苏农业科学,2017,45(17):192.
 Diao Zhihua,et al.Study on wheat disease identification and spraying algorithm in robot system[J].Jiangsu Agricultural Sciences,2017,45(5):192.
[5]刁智华,袁万宾,刁春迎,等.病害特征在作物病害识别中的应用研究综述[J].江苏农业科学,2019,47(05):71.
 Diao Zhihua,et al.Application of disease characteristics in crop disease identification:a review[J].Jiangsu Agricultural Sciences,2019,47(5):71.
[6]林彬彬,邱新法,何永健,等.茶树病害智能诊断识别算法研究[J].江苏农业科学,2019,47(06):85.
 Lin Binbin,et al.Study on intelligent diagnosis and recognition algorithm for tea diseases[J].Jiangsu Agricultural Sciences,2019,47(5):85.
[7]罗巍,陈曙东,王福涛,等.基于深度学习的大型食草动物种群监测方法[J].江苏农业科学,2020,48(20):247.
 Luo Wei,et al.Monitoring method of large herbivore population based on deep learning[J].Jiangsu Agricultural Sciences,2020,48(5):247.
[8]陈恩会,褚姝频,王炜,等.基于RetinaNet模型的梨小食心虫智能识别计数方法[J].江苏农业科学,2021,49(24):205.
 Chen Enhui,et al.Intelligent recognition and counting method of Grapholitha molesta based on RetinaNet model[J].Jiangsu Agricultural Sciences,2021,49(5):205.
[9]何前,郭峰林,方皓正,等.基于改进LeNet-5模型的玉米病害识别[J].江苏农业科学,2022,50(20):35.
 He Qian,et al.Study on maize disease recognition based on improved LeNet-5 model[J].Jiangsu Agricultural Sciences,2022,50(5):35.
[10]孙长兰,林海峰.一种基于集成学习的苹果叶片病害检测方法[J].江苏农业科学,2022,50(20):41.
 Sun Changlan,et al.An apple tree leaf disease detection method based on ensemble learning[J].Jiangsu Agricultural Sciences,2022,50(5):41.

备注/Memo

备注/Memo:
收稿日期:2024-07-14
基金项目:云南省重大科技专项(编号:202202AE090021)。
作者简介:杨宏宇(1998— ),男,辽宁朝阳人,硕士研究生,主要从事机器视觉、机器学习方面的研究。E-mail:2022210044@stu.ynau.edu.cn。
通信作者:张佳进,博士,副教授,主要从事机器视觉、机器学习方面的研究。E-mail:zjjclc@ynau.edu.cn。
更新日期/Last Update: 2025-03-05