|本期目录/Table of Contents|

[1]周绍发,肖小玲,刘忠意,等.改进的基于YOLOv5s苹果树叶病害检测[J].江苏农业科学,2023,51(13):212-220.
 Zhou Shaofa,et al.Improved apple leaf disease detection based on YOLOv5s[J].Jiangsu Agricultural Sciences,2023,51(13):212-220.
点击复制

改进的基于YOLOv5s苹果树叶病害检测(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第13期
页码:
212-220
栏目:
农业工程与信息技术
出版日期:
2023-07-05

文章信息/Info

Title:
Improved apple leaf disease detection based on YOLOv5s
作者:
周绍发肖小玲刘忠意鲁力
长江大学计算机科学学院,湖北荆州 434000
Author(s):
Zhou Shaofaet al
关键词:
苹果树叶病害目标检测YOLOv5sbottleneck transformersSIoU
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对目前在复杂环境下苹果树叶病害检测准确度低、鲁棒性差、计算量大等问题,提出一种改进的基于YOLOv5s苹果树叶病害的检测方法。首先,该方法在YOLOv5s网络基础上,选择考虑方向性的SIoU边框损失函数替代CIoU边框损失函数,使网络训练和推理过程更快,更准确。其次,在特征图转换成固定大小的特征向量的过程中,使用了简单化的快速金字塔池化(SimSPPF)替换快速金字塔池化(SPPF)模块,在不影响效率的情况下丢失的信息更少。最后在主干网络中使用BoTNet(bottleneck transformers)注意力机制,使网络准确的学习到每种病害的独有特征,并且使网络收敛更快。结果表明,相比于基准网络YOLOv5s,改进后的YOLOv5s网络mAP精度为86.5%,计算量为15.5GFLOPs,模型权重大小为13.1 MB,相对于基准YOLOv5s,平均精度提升了6.3百分点、计算量降低了03GFLOPs、模型权重压缩了1 MB。并适用于遮挡、阴影、强光、模糊的复杂环境。本研究所提出的方法,在降低了网络大小、权重、计算量的情况下提高了复杂环境下苹果树叶病害的检测精度,且对复杂环境具有一定的鲁棒性。在预防和治理苹果树叶病害上有较高的实际应用价值,在后续研究上,会扩充更多类别的病害数据集,部署到无人机等物联网设备,从而为实现智能果园种植提供技术参考。
Abstract:
-

参考文献/References:

[1]李会宾,史云. 果园采摘机器人研究综述[J]. 中国农业信息,2019,31(6):1-9.
[2]李书琴,陈聪,朱彤,等. 基于轻量级残差网络的植物叶片病害识别[J]. 农业机械学报,2022,53(3):243-250.
[3]Bari B S,Islam M N,Rashid M,et al. A real-time approach of diagnosing rice leaf disease using deep learning-based faster R-CNN framework[J]. Peer J Computer Science,2021,7:e432.
[4]王超学,祁昕,马罡,等. 基于YOLOv3的葡萄病害人工智能识别系统[J]. 植物保护,2022,48(6):278-288.
[5]Richey B,Shirvaikar M V. Deep learning based real-time detection of northern corn leaf blight crop disease using YOLOv4[C]//Real-Time Image Processing and Deep Learning. 2021:39-45.
[6]Haque M E,Rahman A,Junaeid I,et al. Rice leaf disease classification and detection using YOLOv5[EB/OL]. (2022-09-04)[2022-10-10]. https://arxiv.org/pdf/2209.01579.pdf.
[7]雷建云,陈楚,郑禄,等. 基于改进残差网络的水稻害虫识别[J]. 江苏农业科学,2022,50(14):190-198.
[8]Ultralytics.YOLOv5[EB/OL]. (2020-06-26)[2022-02-22]. https://github.com/ultralytics/YOLOv5.
[9]Rezatofighi H,Tsoi N,Gwak J Y,et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019:658-666.
[10]Zheng Z,Wang P,Liu W,et al. Distance-IoU loss:faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020:12993-13000.
[11]Zheng Z H,Wang P,Ren D W,et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics,2022,52(8):8574-8586.
[12]Gevorgyan Z.SIoU loss:more powerful learning for bounding box regression[EB/OL]. (2022-05-25)[2022-10-10]. https://arxiv.org/abs/2205.12740.
[13]He K M,Zhang X Y,Ren S Q,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[14]Guo M H,Xu T X,Liu J J,et al. Attention mechanisms in computer vision:a survey[J]. Computational Visual Media,2022,8(3):331-368.
[15]Srinivas A,Lin T Y,Parmar N,et al. Bottleneck transformers for visual recognition[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville:IEEE,2021:16514-16524.
[16]Shaw P,Uszkoreit J,Vaswani A.Self-attention with relative position representations[EB/OL]. (2018-04-12)[2022-09-10]. https://arxiv.org/pdf/1803.02155.pdf.

相似文献/References:

[1]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(13):247.
[2]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(13):205.
[3]陶雪阳,施振旦,郭彬彬,等.基于RFID与目标检测的种鹅个体产蛋信息监测方法[J].江苏农业科学,2023,51(5):200.
 Tao Xueyang,et al.Monitoring method of individual egg-laying information of breeding geese based on RFID and object detection[J].Jiangsu Agricultural Sciences,2023,51(13):200.
[4]严陈慧子,田芳明,谭峰,等.基于改进YOLOv4的水稻病害快速检测方法[J].江苏农业科学,2023,51(6):187.
 Yanchen Huizi,et al.Rapid detection method of rice diseases based on improved YOLOv4[J].Jiangsu Agricultural Sciences,2023,51(13):187.
[5]姜国权,杨正元,霍占强,等.基于改进YOLOv5网络的疏果前苹果检测方法[J].江苏农业科学,2023,51(14):205.
 Jiang Guoquan,et al.Apple detection method before thinning fruit based on improved YOLOv5 model[J].Jiangsu Agricultural Sciences,2023,51(13):205.
[6]王圆圆,林建,王姗.基于YOLOv4-tiny模型的水稻早期病害识别方法[J].江苏农业科学,2023,51(16):147.
 Wang Yuanyuan,et al.An early rice disease recognition method based on YOLOv4-tiny model[J].Jiangsu Agricultural Sciences,2023,51(13):147.
[7]倪智涛,胡伟健,李宝山,等.一种基于图像分类与目标检测协同的番茄细粒度病害识别方法[J].江苏农业科学,2023,51(22):221.
 Ni Zhitao,et al.A novel method for tomato fine-grained disease recognition based on image classification and target detection[J].Jiangsu Agricultural Sciences,2023,51(13):221.
[8]施杰,林双双,罗建刚,等.基于YOLO v5s改进模型的玉米作物病虫害检测方法[J].江苏农业科学,2023,51(24):175.
 Shi Jie,et al.Study on a detection method for crop diseases and insect pests based on YOLO v5s improved model[J].Jiangsu Agricultural Sciences,2023,51(13):175.
[9]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.
 Zheng Xukang,et al.Study on pear leaf disease detection based on semi-supervised learning[J].Jiangsu Agricultural Sciences,2024,52(13):192.
[10]温彬彬,张华,孟祥龙.基于改进YOLO v5的轻量化苹果检测方法[J].江苏农业科学,2024,52(12):217.
 Wen Binbin,et al.A lightweight apple detection method based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2024,52(13):217.

备注/Memo

备注/Memo:
收稿日期:2022-10-15
基金项目:国家自然科学基金(编号:61771354)。
作者简介:周绍发(1998—),男,湖北武汉人,硕士研究生,研究方向为深度学习与目标检测。E-mail:2021710595@yangtzeu.edu.cn。
通信作者:肖小玲,博士,教授,研究方向为智能信息处理、网络安全、云计算和无线网络。E-mail:xxl@yangtzeu.edu.cn。
更新日期/Last Update: 2023-07-05