|本期目录/Table of Contents|

[1]郑旭康,李志忠,秦俊豪.基于半监督学习的梨叶病害检测[J].江苏农业科学,2024,52(5):192-201.
 Zheng Xukang,et al.Study on pear leaf disease detection based on semi-supervised learning[J].Jiangsu Agricultural Sciences,2024,52(5):192-201.
点击复制

基于半监督学习的梨叶病害检测(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第5期
页码:
192-201
栏目:
农业工程与信息技术
出版日期:
2024-03-05

文章信息/Info

Title:
Study on pear leaf disease detection based on semi-supervised learning
作者:
郑旭康李志忠秦俊豪
广东工业大学信息工程学院,广东广州510006
Author(s):
Zheng Xukanget al
关键词:
深度学习半监督学习目标检测无标签数据
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
植物病害的检测与识别是一个日益发展的研究领域,随着机器学习和深度学习概念的不断介入,为农业的发展提供了重要的技术支持。然而,目标检测技术存在着带标注数据获取成本高,且需要大量的人工来对数据进行标注等问题,给技术的实际应用造成了一定的阻碍。为解决在使用少量已标注数据及大量未标注数据进行训练模型从而提高准确率的问题,提出一种YOLO目标检测结合self-training半监督学习的方法,并且针对现有的 YOLO v3-Tiny目标检测网络在半监督学习基础上准确率相比于监督学习较低的问题,对原有的YOLO v3-Tiny模型进行了改进。首先,使用空间金字塔池化结构对主干网络的多尺度特征进行融合;其次,将YOLO v3-Tiny检测头部分的标准卷积层替换成GSConv;最后,运用BiFPN结构对中间部分的特征与检测头部分的多尺度特征进行双向融合。本研究提出的基于半监督学习的改进型YOLO v3-Tiny网络可以快速准确地检测出梨叶上的病斑,在试验中,准确度、召回率、平均精度分别达到97.07%、93.78%、97.51%,对于快速准确地诊断出梨叶病斑的危害程度并且及时进行防治具有十分重要的意义。
Abstract:
-

参考文献/References:

[1]Wu J,Wang Z W,Shi Z B,et al. The genome of the pear (Pyrus bretschneideri Rehd.)[J]. Genome Research,2013,23(2):396-408.
[2]Yang W L,Fan S S,Xu S X,et al. Autonomous underwater vehicle navigation using sonar image matching based on convolutional neural network[J]. IFAC-Papers OnLine,2019,52(21):156-162.
[3]马博宇,尉寅玮. 基于AdaBoost算法的人脸识别系统的研究与实现[J]. 仪器仪表学报,2016,37(增刊1):162-167.
[4]Zhang L L,Lin L,Liang X D,et al. Is faster R-CNN doing well for pedestrian detection?[C]//European Conference on Computer Vision.Cham:Springer,2016:443-457.
[5]李建兴,刘振宇,马莹,等. 基于YOLO v4的胡瓜钝绥螨自动检测计数[J]. 江苏农业科学,2022,50(14):199-207.
[6]Yan Q A,Yang B H,Wang W Y,et al. Apple leaf diseases recognition based on an improved convolutional neural network[J]. Sensors,2020,20(12):3535.
[7]Tao Y,Cuicu L. Recognition system for leaf diseases of ophiopogon japonicus based on PCA-SVM[J]. Plant Diseases and Pests,2020,11(2):9-13.
[8]Zeng L X,Irwin K. Introduction to semi-supervised learning[M]. Taylor and Francis:CRC Press,2013:1-250.
[9]Sajjadi M,Javanmardi M,Tasdizen T.Regularization with stochastic transformations and perturbations for deep semi-supervised learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.December 5 - 10,2016,Barcelona,Spain.New York:ACM,2016:1171-1179.
[10]Zhang X,He B,Luo T J. Training query filtering for semi-supervised learning to rank with pseudo labels[J]. World Wide Web,2016,19(5):833-864.
[11]Laine S,Aila T. Temporal ensembling for semi-supervised learning[J]. CoRR,2016,abs/1610.02242.
[12]Sohn K,Berthelot D,Li C L,et al. FixMatch:simplifying semi-supervised learning with consistency and confidence[EB/OL]. 2020:arXiv:2001.07685.https://arxiv.org/abs/2001.07685.pdf.
[13]Zhang Y,Shi B M. Improving pooling method for regularization of convolutional networks based on the failure probability density[J]. Optik,2017,145:258-265.
[14]Srivastava N,Hinton G,Krizhevsky A,et al. Dropout:a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research,2014,15(1):1929-1958.
[15]Huang G,Sun Y,Liu Z A,et al. Deep networks with stochastic depth[M]//Computer Vision – ECCV 2016.Cham:Springer International Publishing,2016:646-661.
[16]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 (CVPR).June 27-30,2016,Las Vegas,NV,USA.IEEE,2016:779-788.
[17]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.
[18]Liu W,Anguelov D,Erhan D,et al. SSD:single shot MultiBox detector[EB/OL]. 2015:arXiv:1512.02325.https://arxiv.org/abs/1512.02325.pdf.
[19]Jeong J,Lee S,Kim J,et al. Consistency-based semi-supervised learning for object detection[C]. Proceedings of the 33rd International Conference on Neural Information Processing Systems,2019,965:10759-10768.
[20]Bilen H,Vedaldi A. Weakly supervised deep detection networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).June 27-30,2016,Las Vegas,NV,USA. IEEE,2016:2846-2854.
[21]Zhu Y,Zhang Z Y,Wu C R,et al. Improving semantic segmentation via efficient self-training[J]. arxix:2004.14960v2.
[22]Triguero I,García S,Herrera F. Self-labeled techniques for semi-supervised learning:taxonomy,software and empirical study[J]. Knowledge and Information Systems,2015,42(2):245-284.
[23]刘军,后士浩,张凯,等. 基于增强Tiny YOLO v3算法的车辆实时检测与跟踪[J]. 农业工程学报,2019,35(8):118-125.
[24]Farhadi A,Redmon J. YOLO v3:an incremental improvement[C]//Computer vision and pattern recognition. Berlin/Heidelberg,Germany:Springer,2018,1804:1-6.
[25]Wang C Y,Bochkovskiy A,Liao H Y M. YOLO v7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 17-24,2023,Vancouver,BC,Canada.IEEE,2023:7464-7475.
[26]Yuan X,Fang S T,Li N,et al. Performance comparison of sea cucumber detection by the YOLO v5 and DETR approach[J]. JMSE,2023,11(11):2043.
[27]Zhang Y N,Kong J,Qi M A,et al. Object detection based on multiple information fusion net[J]. Applied Sciences,2020,10(1):418.
[28]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).June 13-19,2020,Seattle,WA,USA.IEEE,2020:10778-10787.
[29]Li H L,Li J,Wei H B,et al. Slim-neck by GSConv:a better design paradigm of detector architectures for autonomous vehicles[EB/OL]. 2022:arXiv:2206.02424.https://arxiv.org/abs/2206.02424.pdf.
[30]Fenu G,Malloci F M. DiaMOS plant:a dataset for diagnosis and monitoring plant disease[J]. Agronomy,2021,11(11):2107.
[31]Peng S D,Jiang W,Pi H J,et al. Deep snake for real-time instance segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 13-19,2020,Seattle,WA,USA.IEEE,2020:8530-8539.

相似文献/References:

[1]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241.
 Liang Wanjie,et al.Identification of rice insect pests based on CNN model[J].Jiangsu Agricultural Sciences,2017,45(5):241.
[2]赵建敏,李艳,李琦,等.基于卷积神经网络的马铃薯叶片病害识别系统[J].江苏农业科学,2018,46(24):251.
 Zhao Jianmin,et al.Potato leaf disease identification system based on convolutional neural network[J].Jiangsu Agricultural Sciences,2018,46(5):251.
[3]李懿超,沈润平,黄安奇.基于深度学习的湘赣鄂地区植被变化及其影响因子关系模型[J].江苏农业科学,2019,47(03):213.
 Li Yichao,et al.Study on relational model between vegetation change and its impact factors based on deep learning in Hunan, Jiangxi and Hubei areas[J].Jiangsu Agricultural Sciences,2019,47(5):213.
[4]刘嘉政.基于深度迁移学习模型的花卉种类识别[J].江苏农业科学,2019,47(20):231.
 Liu Jiazheng.Flower species identification based on deep transfer learning model[J].Jiangsu Agricultural Sciences,2019,47(5):231.
[5]荆伟斌,胡海棠,程成,等.基于深度学习的地面苹果识别与计数[J].江苏农业科学,2020,48(05):210.
 Jing Weibin,et al.Recognition and counting of ground apples based on deep learning[J].Jiangsu Agricultural Sciences,2020,48(5):210.
[6]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.
[7]孙孝龙,徐森,周卫阳,等.基于物联网和深度学习的养蚕智能监控系统设计[J].江苏农业科学,2020,48(21):241.
 Sun Xiaolong,et al.Design of an intelligent monitoring system for sericulture based on internet of things and deep learning[J].Jiangsu Agricultural Sciences,2020,48(5):241.
[8]康飞龙,李佳,刘涛,等.多类农作物病虫害的图像识别应用技术研究综述[J].江苏农业科学,2020,48(22):22.
 Kang Feilong,et al.Application technology of image recognition for various crop diseases and insect pests: a review[J].Jiangsu Agricultural Sciences,2020,48(5):22.
[9]李彧,余心杰,郭俊先.基于全卷积神经网络方法的玉米田间杂草识别[J].江苏农业科学,2022,50(6):93.
 Li Yu,et al.Weed recognition in corn field based on fully convolutional neural network (FCN) method[J].Jiangsu Agricultural Sciences,2022,50(5):93.
[10]孙东来,王继超,陈科,等.基于Ghost-YOLOv3-2算法的2尺度猪目标检测[J].江苏农业科学,2022,50(7):189.
 Sun Donglai,et al.Two-scale pig target detection based on Ghost-YOLOv3-2[J].Jiangsu Agricultural Sciences,2022,50(5):189.
[11]孔江波,朱贺,张延文,等.基于实例置信度推断的半监督小样本植物病害图像识别[J].江苏农业科学,2022,50(12):229.
 Kong Jiangbo,et al.Semi-supervised few-shot plant disease image recognition based on instance credibility inference[J].Jiangsu Agricultural Sciences,2022,50(5):229.

备注/Memo

备注/Memo:
收稿日期:2023-03-27
基金项目:广东省自然科学基金(编号:2019A1515011371);广东省省级科技计划(产学研)(编号:2016B090918031)。
作者简介:郑旭康(1999—),男,广西柳州人,硕士,研究方向为计算机视觉领域。E-mail:1412154348@qq.com。
通信作者:李志忠,博士,副教授,硕士生导师,研究方向为数字电源技术、人工智能。E-mail:leezz1@163.com。
更新日期/Last Update: 2024-03-05