[1]承达瑜,赵伟,何伟德,等. 基于改进YOLOv5n模型的农作物病虫害识别方法[J].江苏农业学报,2024,(11):2021-2031.[doi:doi:10.3969/j.issn.1000-4440.2024.11.005]
　CHENG DayuZHAO WeiHE WeideWU ZepengWANG Jiandong. Identification method of crop diseases and insect pests based on improved YOLOv5n model[J].,2024,(11):2021-2031.[doi:doi:10.3969/j.issn.1000-4440.2024.11.005]
点击复制

 基于改进YOLOv5n模型的农作物病虫害识别方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年11期
页码:
2021-2031
栏目:
出版日期:
2024-11-30

文章信息/Info

Title:
 Identification method of crop diseases and insect pests based on improved YOLOv5n model
作者:
承达瑜; 赵伟; 何伟德; 武择鹏; 王建东
 (1.河北工程大学矿业与测绘工程学院,河北邯郸056038)
Author(s):
CHENG DayuZHAO WeiHE WeideWU ZepengWANG Jiandong
 (1.School of Mining and Geomatics Engineering, Hebei University of Engineering, Handan 056038, China)
关键词:
 ; 农业病虫害; 目标检测; 轻量级模型; 注意力机制
Keywords:
 ; agricultural pest and disease; object detection; lightweight model; attention mechanism
分类号:
S435
DOI:
doi:10.3969/j.issn.1000-4440.2024.11.005
文献标志码:
A
摘要:
 针对模型对复杂场景下农作物病虫害的识别精度低、模型参数量大的问题,本研究对轻量级YOLOv5n模型进行改进。首先,在YOLOv5n模型的骨干网络中加入坐标注意力模块,使模型关注检测目标及其位置,减少复杂背景对模型的影响。其次,引入加权的双向特征融合金字塔网络(BiFPN),减少小目标信息丢失,提高了模型的特征学习能力。最后,用损失函数SIoU代替损失函数CIoU,在不改变模型参数量的情况下,提升了目标检测精度。在无人机采集到的玉米病虫害数据集上,本研究提出的AgriPest-YOLOv5n模型的mAP@0.50达81.32%,在Jetson Xavier开发板上检测速度达到77 FPS,模型大小为1.63 MB。改进后的YOLOv5n模型能够满足轻量化的要求,能够实时、准确地识别复杂背景下的农作物病虫害,本研究结果可为病虫害精准防治提供技术支持。
Abstract:
 In order to solve the problems of low recognition accuracy for crop diseases and insect pests in complex scenes and large model parameters of the model, the lightweight YOLOv5n model was improved in this study. Firstly, a coordinate attention module was added to the backbone network of YOLOv5n model to make the model focus on the detection target and its location and reduce the influence of complex background on the model. Secondly, the weighted bi-directional feature fusion pyramid network (BiFPN) was introduced to reduce the information loss of small targets and improve the model’s feature learning ability. Finally, the loss function SIoU was used to replace the loss function CIoU, which improved the target detection accuracy without changing the parameters of the model. In the dataset of corn pests and diseases collected by unmanned air vehicle, the AgriPest-YOLOv5n model mAP@0.50 proposed by this study reached 81.32%, and the detection speed reached 77 FPS on the Jetson Xavier development board. The size of the model was 1.63 MB. The improved YOLOv5n model can meet the requirement of light weight, and can identify crop diseases and insect pests in real time and accurately under complex background. The results of this study provide technical support for the precision control of crop diseases and insect pests.

参考文献/References:

 

[1]TIAN Y N, WANG S H, LI E, et al. MD-YOLO:multi-scale dense YOLO for small target pest detection[J]. Computers and Electronics in Agriculture,2023,213:108233.

<br/>[2]王吉芸,胡彦,杨春震,等. 云南省杧果主要病虫害发生与绿色防控措施概述[J]. 中国植保导刊,2023,43(11):60-64.

<br/>[3]廖娟,陶婉琰,臧英,等. 农作物病虫害遥感监测关键技术研究进展与展望[J]. 农业机械学报,2023,54(11):1-19.

<br/>[4]NGUGI L C, ABELWAHAB M, ABO-ZAHHAD M. Recent advances in image processing techniques for automated leaf pest and disease recognition-a review[J]. Information Processing in Agriculture,2021,8(1):27-51.

<br/>[5]PADOL P B, SAWANT S D. Fusion classification technique used to detect downy and Powdery Mildew grape leaf diseases[C]//IEEE. 2016 International Conference on Global Trends in Signal Processing,Information Computing and Communication. Jalgaon:IEEE,2016.

<br/>[6]高雄, 汤岩, 陈铁英, 等. 基于图像处理的甘蓝虫害识别研究[J]. 江苏农业科学,2017,45(23):235-238.

<br/>[7]李海, 李谊骏, 陈诗果, 等. 苹果树病虫害智能识别系统设计与实现[J]. 科学技术与工程,2021,21(25):10639-10645.

<br/>[8]DEY A K, SHARMA M, MESHRAM M R. Image processing based leaf rot disease,detection of betel vine (Piper betle L.)[J]. Procedia Computer Science,2016,85:748-754.

<br/>[9]TIAN Y N， YANG G D， WANG Z， et al. Instance segmentation of apple flowers using the improved mask R–CNN model[J]. Biosystems Engineering,2020,193:264-278.

<br/>[10]WANG X W, ZHAO Q Z, JIANG P, et al. LDS-YOLO:a lightweight small object detection method for dead trees from shelter forest[J]. Computers and Electronics in Agriculture,2022,198:107035.

<br/>[11]王铭慧,张怀清,樊江川,等. 基于深度学习网络实现番茄病虫害检测与识别[J]. 中国农业大学学报,2023,28(11):165-181.

<br/>[12]李就好,林乐坚,田凯,等. 改进Faster R-CNN的田间苦瓜叶部病害检测[J]. 农业工程学报,2020,36(12):179-185.

<br/>[13]WANG R J, JIAO L, XIE C J, et al. S-RPN:sampling-balanced region proposal network for small crop pest detection[J]. Computers and Electronics in Agriculture,2021,187:106290.

<br/>[14]宋中山,汪进,郑禄,等. 基于二值化的Faster R-CNN柑橘病虫害识别研究[J]. 中国农机化学报,2022,43(6):150-158.

<br/>[15]张善文,邵彧,齐国红,等. 基于多尺度注意力卷积网络的作物害虫检测[J]. 江苏农业学报,2021,37(3):579-588.

<br/>[16]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified,real-time object detection[C]//IEEE/CVF. 2016 IEEE conference on computer vision and pattern recognition. Las Vegas,NV:IEEE,2016.

<br/>[17]吕石磊,卢思华,李震,等. 基于改进YOLOv3-LITE轻量级神经网络的柑橘识别方法[J]. 农业工程学报,2019,35(17):205-214.

<br/>[18]储鑫,李祥,罗斌,等. 基于改进YOLOv4算法的番茄叶部病害识别方法[J]. 江苏农业学报,2023,39(5):1199-1208.

<br/>[19]周维,牛永真,王亚炜,等. 基于改进的YOLOv4-GhostNet水稻病虫害识别方法[J]. 江苏农业学报,2022,38(3):685-695.

<br/>[20]骆润玫,殷惠莉,刘伟康,等. 基于YOLOv5-C的广佛手病虫害识别[J]. 华南农业大学学报,2023,44(1):151-160.

<br/>[21]XUE Z Y, XU R J, BAI D, et al. YOLO-tea:a tea disease detection model improved by YOLOv5[J]. Forests,2023,14(2):415.

<br/>[22]张友为,王鑫鑫,范晓飞. 基于深度学习的玉米和番茄病虫害检测技术研究进展[J]. 江苏农业科学,2024,52(10):10-20.

<br/>[23]吴子炜,夏芳,陆林峰,等. 基于改进YOLOv5的水稻主要害虫识别方法[J]. 江苏农业科学,2023,51(21):218-224.

<br/>[24]路阳,刘婉婷,林立媛,等. CNN与BiLSTM相结合的水稻病害识别新方法[J]. 江苏农业科学,2023,51(20):211-217.

<br/>[25]WU X P, ZHAN C, LAI Y K, et al. Ip102:a large-scale benchmark dataset for insect pest recognition[C]//IEEE/CVF. 2019 IEEE/CVF conference on computer vision and pattern recognition. Long Beach,CA:IEEE,2019.

<br/>[26]HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//IEEE/CVF. 2018 IEEE conference on computer vision and pattern recognition. Salt Lake City,UT:IEEE,2018.

<br/>[27]HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//IEEE/CVF. 2021 IEEE/CVF conference on computer vision and pattern recognition. Nashville,TN:IEEE,2021.

<br/>[28]TAN M X, PANG R M, LE Q V. Efficientdet:Scalable and efficient object detection[C]//IEEE/CVF. 2020 IEEE/CVF conference on computer vision and pattern recognition. Seattle,WA:IEEE,2020.

<br/>[29]CHEN F X, ZHANG L X, KANG S Y, et al. Soft-NMS-enabled YOLOv5 with SIOU for small water surface floater detection in UAV-captured images[J]. Sustainability,2023,15(14):10751.

备注/Memo

备注/Memo:
收稿日期：2024-01-29
基金项目：河北省重大科技成果转化专项(22287401Z)；国家自然科学基金项目(42071246)
作者简介：承达瑜(1980-),男,江苏常州人,博士,副教授,主要从事地理大数据挖掘、作物长势遥感监测及计算机视觉技术研究。(E-mail)yuyumails@126.com
通讯作者：赵伟,(E-mail)davgis@163.com
更新日期/Last Update: 2025-01-20