|本期目录/Table of Contents|

[1]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):41-47.
 Sun Changlan,et al.An apple tree leaf disease detection method based on ensemble learning[J].Jiangsu Agricultural Sciences,2022,50(20):41-47.
点击复制

一种基于集成学习的苹果叶片病害检测方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第50卷
期数:
2022年第20期
页码:
41-47
栏目:
“表型组学”专栏
出版日期:
2022-10-20

文章信息/Info

Title:
An apple tree leaf disease detection method based on ensemble learning
作者:
孙长兰林海峰
南京林业大学信息科学技术学院,江苏南京 210037
Author(s):
Sun Changlanet al
关键词:
苹果树叶片病害特征提取集成学习病害识别机器学习
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
由于苹果树叶片病害图像背景复杂、病斑形态多样,苹果树叶片病害的检测一直是一项具有挑战性的任务。传统的苹果树叶片病害检测方法严重依赖于果农经验和特定领域的专家,步骤复杂且低效,并很容易导致病害的误判和漏判。为解决该问题,基于深度学习技术对苹果树叶片病害特征进行自适应学习和提取,提出一种基于集成学习的苹果树叶片病害检测方法。该算法基于不同的模型,在处理不同的数据集上呈现出各自的特性,充分利用了模型间的优势互补,使用非极大值抑制算法将YOLOv5和EfficientDet模型进行集成,进一步提高模型特征提取能力并且增强了模型的检测能力。结果表明,该方法在不增加延迟的情况下,能有效提高3种苹果树叶片病害的检测效果,平均精度可达73.4%,相比于单个YOLOv5和EfficientDet模型分别提高了3.0%、4.8%。集成后的算法具有更好的特征提取能力,可以提取到更多的病害特征信息,并且较好地平衡了模型的识别精度与模型复杂度,可为田间环境下苹果树叶片病害识别提供参考。
Abstract:
-

参考文献/References:

[1]乔社茹. 苹果叶部病害的识别与防治[J]. 山西林业科技,2020,49(2):55-57.
[2]边柯橙,杨海军,路永华. 深度学习在农业病虫害检测识别中的应用综述[J]. 软件导刊,2021,20(3):26-33.
[3]周敏敏. 基于迁移学习的苹果叶面病害Android检测系统研究[D]. 杨凌:西北农林科技大学,2019.
[4]Jiang P,Chen Y H,Liu B,et al. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks[J]. IEEE Access,2019,7:59069-59080.
[5]邸洁,曲建华. 基于Tiny-YOLO的苹果叶部病害检测[J]. 山东师范大学学报(自然科学版),2020,35(1):78-83.
[6]李鑫然,李书琴,刘斌. 基于改进Faster R_CNN的苹果叶片病害检测模型[J]. 计算机工程,2021,47(11):298-304.
[7]李鑫然. 基于深度学习的苹果叶片病害检测方法研究[D]. 杨凌:西北农林科技大学,2021.
[8]鲍文霞,吴刚,胡根生,等. 基于改进卷积神经网络的苹果叶部病害识别[J]. 安徽大学学报(自然科学版),2021,45(1):53-59.
[9]余小东,杨孟辑,张海清,等. 基于迁移学习的农作物病虫害检测方法研究与应用[J]. 农业机械学报,2020,51(10):252-258.
[10]曹珊珊.苹果内部缺陷的无损检测研究[D]. 保定:河北农业大学,2020.
[11]Yadav D,Akanksha,Yadav A K. A novel convolutional neural network based model for recognition and classification of apple leaf diseases[J]. Traitement Du Signal,2020,37(6):1093-1101.
[12]Ultralytics. YOLOv5[Z/OL]. (2021-09-01)[2021-10-02]. https://github.com/ultralytics/yolov5.
[13]Tan M X,Pang R M,Le Q V. EfficientDet:scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,WA,USA,2020:10778-10787.
[14]PlantVillage Dataset[DS/OL]. (2021-08-01)[2021-10-02]. https://www.kaggle.com/abdallahalidev/plantvillage-dataset.
[15]普措才仁,秦亚红. 基于深度学习模型的非结构化数据标注方法研究[J]. 西北民族大学学报(自然科学版),2020,41(2):14-19,44.
[16]Lee Y,Im D,Shim J. Data labeling research for deep learning based fire detection system[C]//2019 International Conference on Systems of Collaboration Big Data,Internet of Things & Security (SysCoBIoTS). 2019,Casablanca,Morocco,2019:1-4.
[17]Redmon 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. Las Vegas,NV,USA.IEEE,2016:779-788.
[18]Lin T Y,Maire M,Belongie S,et al. Microsoft coco:common objects in context[C]//European Conference on Computer Vision. Springer,Cham,2014:740-755.
[19]Everingham M,Eslami S M A,Gool L,et al. The pascal visual object classes challenge:a retrospective[J]. International Journal of Computer Vision,2015,111(1):98-136.
[20]Wang C Y,Liao H Y M,Wu Y H,et al. CSPNet:a new backbone that can enhance learning capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle,WA,USA,2020:1571-1580.
[21]Liu S,Qi L,Qin H F,et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,UT,USA,2018:8759-8768.
[22]Tan M X,Pang R M,le Q V.EfficientDet:scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,WA,USA,2020:10778-10787.
[23]Tan M X,Le Q V. Efficientnet:Rethinking model scaling for convolutional neural networks[C]//36th International Conference on Machine Learning. California,2019:6105-6114.
[24]陈志韬,殷恺铭,张洋,等. 基于EfficientDet的安全帽佩戴检测研究[J]. 信息技术与标准化,2021(增刊1):19-23,29.
[25]Neubeck A,Van Gool L. Efficient non-maximum suppression[C]//18th International Conference on Pattern Recognition (ICPR06),Hong Kong,2006:850-855.
[26]Bottou L.Large-scale machine learning with stochastic gradient descent[M]//Lechevallier Y,Saporta G. Proceedings of COMPSTAT’2010. New York:Physica-Verlag HD. 2010:177-186.
[27]Loshchilov I,Hutter F. Decoupled weight decay regularization[C]//ICLR 2019,2019.
[28]张志达,黄鹏,刘洋,等. 基于YOLO算法与深度学习的证件质量检测系统[J]. 单片机与嵌入式系统应用,2021,21(7):67-70.

相似文献/References:

[1]刘宗泉,李梅花,徐秀丽,等.江苏省丰县苹果树病虫发生种类与危害特点[J].江苏农业科学,2014,42(12):188.
 Liu Zongquan,et al.Types and damage characteristics of pests and diseases of apple trees in Fengxian County,Jiangsu Province[J].Jiangsu Agricultural Sciences,2014,42(20):188.
[2]刘钰娇,刘伟,王娟,等.修剪工具对苹果树腐烂病菌的传播作用[J].江苏农业科学,2014,42(08):127.
 Liu Yujiao,et al.Effect of pruning tools on dissemination of Valsa mali[J].Jiangsu Agricultural Sciences,2014,42(20):127.
[3]樊景超,丘耘,周国民.基于序列图像的苹果树三维点云模型获取[J].江苏农业科学,2016,44(10):375.
 Fan Jingchao,et al.Acquisition of 3D point cloud model of apple tree based on sequence image[J].Jiangsu Agricultural Sciences,2016,44(20):375.
[4]尹宝重,刘博燕,刘盼,等.苹果树皮内生菌对苹果树腐烂病的防治效果[J].江苏农业科学,2017,45(10):84.
 Yin Baozhong,et al.Control effect of apple bark endophytic bacteria on apple tree rot disease[J].Jiangsu Agricultural Sciences,2017,45(20):84.
[5]刘芳洁.紫苏不同部位乙醇提取物对苹果树腐烂病的影响及机制[J].江苏农业科学,2018,46(17):97.
 Liu Fangjie.Effect and mechanism of ethanol extracts from different parts of Perilla frutescens on apple tree canker[J].Jiangsu Agricultural Sciences,2018,46(20):97.
[6]刘亚娜,刘世增,王芳,等.穴贮肥水和秸秆覆盖对苹果树光合及叶绿素荧光特性的影响[J].江苏农业科学,2023,51(14):164.
 Liu Yana,et al.Impacts of hole fertilizer storage and straw mulching on photosynthesis and chlorophyll fluorescence of apple trees[J].Jiangsu Agricultural Sciences,2023,51(20):164.
[7]曾晏林,贺壹婷,蔺瑶,等.基于BCE-YOLOv5的苹果叶部病害检测方法[J].江苏农业科学,2023,51(15):155.
 Zeng Yanlin,et al.An apple leaf disease detection method based on BCE-YOLOv5[J].Jiangsu Agricultural Sciences,2023,51(20):155.
[8]马晓,邢雪,武青海.基于改进ConvNext的复杂背景下玉米叶片病害分类[J].江苏农业科学,2023,51(19):190.
 Ma Xiao,et al.Maize leaf disease classification under complex background based on improved ConvNext[J].Jiangsu Agricultural Sciences,2023,51(20):190.
[9]李大华,仲婷,王笋,等.基于改进ShuffleNet v2的轻量化番茄叶片病害识别[J].江苏农业科学,2024,52(3):220.
 Li Dahua,et al.Lightweight disease identification for tomato leaves based on improved ShuffleNet v2[J].Jiangsu Agricultural Sciences,2024,52(20):220.
[10]马维娣,吴钦木.基于改进轻量化网络MobileViT的苹果树叶病害识别[J].江苏农业科学,2024,52(3):229.
 Ma Weidi,et al.Apple leaf disease identification based on improved lightweight network MobileViT[J].Jiangsu Agricultural Sciences,2024,52(20):229.

备注/Memo

备注/Memo:
收稿日期:2021-10-19
基金项目:江苏省现代农机装备与技术示范推广项目(编号:NJ2021-19);江苏省重点研发计划(编号:BE2021716);江苏省农业科技自主创新资金[编号:CX(20)3038]。
作者简介:孙长兰(1996—),女,安徽六安人,硕士研究生,主要从事农林业病虫害的研究。E-mail:sunchanglan@njfu.edu.cn。
通信作者:林海峰,博士,副教授,主要从事农业物联网和农林人工智能系统研究。E-mail:haifeng.lin@njfu.edu.cn。
更新日期/Last Update: 2022-10-20