[1]李志良,李梦霞,董勇,等.基于改进YOLO v8的轻量化玉米害虫识别方法[J].江苏农业科学,2024,52(14):196-206.
 Li Zhiliang,et al.Lightweight corn pest recognition method based on enhanced YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(14):196-206.
点击复制

基于改进YOLO v8的轻量化玉米害虫识别方法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第14期
页码:
196-206
栏目:
农业工程与信息技术
出版日期:
2024-07-20

文章信息/Info

Title:
Lightweight corn pest recognition method based on enhanced YOLO v8
作者:
李志良1李梦霞1董勇2李龙1
1.长江大学计算机科学学院,湖北荆州434000; 2.长江大学信息与数学学院,湖北荆州434000
Author(s):
Li Zhilianget al
关键词:
玉米害虫识别YOLO v8EfficientNet-B0RepVGGMPDIoU
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对目前玉米害虫识别领域中识别算法参数量大、计算量大导致玉米害虫识别算法不能部署在移动智慧农业设备中及玉米害虫识别算法检测精度低等问题,基于网络复杂程度最小的YOLO v8n,提出一种轻量化玉米害虫识别算法YOLO v8n-ERM。首先,在骨干特征提取网络引入EfficientNet-B0轻量化网络,通过对神经网络模型进行缩放,采用深度可分离卷积,有效降低了模型参数量、计算量;在颈部网络中引入RepVGG结构重参数化模块,融合多分支特征以提升模型的检测精度,同时有效降低模型的计算量;最后,用MPDIoU损失函数替换原损失函数,使最终预测框更接近真实框。用本研究算法处理数据增强后的IP102数据集,结果表明,相较于基线模型YOLO v8n,YOLO v8n-ERM算法的参数量为2.4 M,计算量为3.7 GFLOPs,二者分别下降了0.6 M、4.4 GFLOPs,而且YOLO v8n-ERM算法的mAP@0.5、mAP@0.5 ∶0.95分别为91.8%、62.0%,相较于基线模型分别提升了3.6、2.1百分点,表明使用更少的参数量、计算量得到了更高的精度。另外在黑暗、有遮挡、个体重叠及害虫与环境背景相似的复杂环境下的处理结果表明,YOLO v8n-ERM算法能够准确识别出玉米害虫个体,极大降低了复杂环境下的漏检率,具有一定的鲁棒性,可为玉米病虫害的数字智能防控提供技术支持。
Abstract:
-

参考文献/References:

[1]刘杰,曾娟,杨清坡,等. 2023年农作物重大病虫害发生趋势预报[J]. 中国植保导刊,2023,43(1):32-35.
[2]Cheng X,Zhang Y H,Chen Y Q,et al. Pest identification via deep residual learning in complex background[J]. Computers and Electronics in Agriculture,2017,141:351-356.
[3]Zheng L,Shen L Y,Tian L,et al. Scalable person re-identification:a benchmark[C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE,2015:1116-1124.
[4]翟肇裕,曹益飞,徐焕良,等. 农作物病虫害识别关键技术研究综述[J]. 农业机械学报,2021,52(7):1-18.
[5]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):190-197.
[6]张航,程清,武英洁,等. 一种基于卷积神经网络的小麦病害识别方法[J]. 山东农业科学,2018,50(3):137-141.
[7]周绍发,肖小玲,刘忠意,等. 改进的基于YOLO v5s苹果树叶病害检测[J]. 江苏农业科学,2023,51(13):212-220.
[8]Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago,Chile.IEEE,2015:1440-1448.
[9]Jiang P Y,Ergu D J,Liu F Y,et al. A review of yolo algorithm developments[J]. Procedia Computer Science,2022,199:1066-1073.
[10]Teng Y,Zhang J,Dong S F,et al. MSR-RCNN:a multi-class crop pest detection network based on a multi-scale super-resolution feature enhancement module[J]. Frontiers in Plant Science,2022,13:810546.
[11]陈峰,谷俊涛,李玉磊,等. 基于机器视觉和卷积神经网络的东北寒地玉米害虫识别方法[J]. 江苏农业科学,2020,48(18):237-244.
[12]Jia L Q,Wang T,Chen Y,et al. MobileNet-CA-YOLO:an improved YOLO v7 based on the MobileNet v3 and attention mechanism for rice pests and diseases detection[J]. Agriculture,2023,13(7):1285.
[13]段新涛,王伸,赵晴,等. 基于改进YOLO v4的夏玉米主要害虫检测方法研究[J]. 山东农业科学,2023,55(10):167-173.
[14]Zhang L J,Ding G C,Li C R,et al. DCF-YOLO v8:an improved algorithm for aggregating low-level features to detect agricultural pests and diseases[J]. Agronomy,2023,13(8):2012.
[15]慕君林,马博,王云飞,等. 基于深度学习的农作物病虫害检测算法综述[J]. 农业机械学报,2023,54(增刊2):301-313.
[16]Wu X P,Zhan C,Lai Y K,et al. IP102:a large-scale benchmark dataset for insect pest recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach,CA,USA.IEEE,2019:8779-8788.
[17]Tan M X,Le Q V. EfficientNet:rethinking model scaling for convolutional neural networks[EB/OL]. [2023-11-11]. http://arxiv.org/abs/1905.11946.
[18]Ding X H,Zhang X Y,Ma N N,et al. RepVGG:making VGG-style ConvNets great again[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville,TN,USA.IEEE,2021:13728-13737.
[19]Ma S L,Xu Y. MPDIoU:a loss for efficient and accurate bounding box regression[EB/OL]. [2023-11-11]. http://arxiv.org/abs/2307.07662.
[20]Zhou D Q,Hou Q B,Chen Y P,et al. Rethinking bottleneck structure for efficient mobile network design[C]//Vedaldi A,Bischof H,Brox T,et al. European Conference on Computer Vision.Cham:Springer,2020:680-697.
[21]Ma N N,Zhang X Y,Zheng H T,et al. ShuffleNet v2:practical guidelines for efficient CNN architecture design[C]//Computer Vision -ECCV 2018:15th European Conference,Munich,Germany,September 8-14,2018,Proceedings,Part ⅩⅣ. ACM,2018:122-138.
[22]Howard A,Sandler M,Chen B,et al. Searching for MobileNet v3[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul,Korea (South).IEEE,2019:1314-1324.

相似文献/References:

[1]叶琪,王丽芬,马明涛,等.基于改进YOLO v8的草莓病害检测方法[J].江苏农业科学,2024,52(20):250.
 Ye Qi,et al.Strawberry disease detection method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(14):250.
[2]李龙,李梦霞,李志良.基于改进YOLO v8的水稻害虫识别方法[J].江苏农业科学,2024,52(20):209.
 Li Long,et al.Rice pest identification method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(14):209.
[3]张立强,武玲梅,蒋林利,等.基于改进YOLO v8s的葡萄叶片病害检测[J].江苏农业科学,2024,52(21):221.
 Zhang Liqiang,et al.Detection of grape leaf disease based on improved YOLO v8s[J].Jiangsu Agricultural Sciences,2024,52(14):221.
[4]鲍宜帆,张一丹,樊彩霞,等.基于深度学习的草莓成熟度检测方法[J].江苏农业科学,2025,53(5):89.
 Bao Yifan,et al.Study on strawberry maturity detection method based on deep learning[J].Jiangsu Agricultural Sciences,2025,53(14):89.
[5]沈桂芳,张平.基于改进YOLO v8的温室草莓成熟度智能实时识别[J].江苏农业科学,2025,53(5):62.
 Shen Guifang,et al.Intelligent real-time recognition of strawberry maturity in greenhouses based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2025,53(14):62.
[6]曾林涛,马嘉昕,丁羽,等.基于改进YOLO v8的苹果叶部病害检测方法[J].江苏农业科学,2025,53(5):147.
 Zeng Lintao,et al.An apple leaf disease detection method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2025,53(14):147.
[7]李孝晖,谭峰,陈雪,等.基于改进YOLO v8FDE的大豆田间杂草识别方法[J].江苏农业科学,2025,53(20):202.
 Li Xiaohui,et al.A weed recognition method for soybean field based on improved YOLO v8FDE[J].Jiangsu Agricultural Sciences,2025,53(14):202.
[8]梁岩,苏恒强.基于改进YOLO v8s的玉米病害程度检测模型[J].江苏农业科学,2025,53(20):296.
 Liang Yan,et al.A maize disease severity detection model based on improved YOLO v8s[J].Jiangsu Agricultural Sciences,2025,53(14):296.
[9]王婵,朱劲松,周军.基于改进YOLO v8的轻量级水稻病虫害识别模型[J].江苏农业科学,2025,53(20):232.
 Wang Chan,et al.A lightweight rice pest and disease recognition model based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2025,53(14):232.
[10]王少芳,陈贤,崔艳荣,等.基于HTWYOLO的轻量化草莓病害检测方法[J].江苏农业科学,2025,53(20):262.
 Wang Shaofang,et al.A lightweight strawberry disease detection method based on HTWYOLO[J].Jiangsu Agricultural Sciences,2025,53(14):262.

备注/Memo

备注/Memo:
收稿日期:2024-01-14
基金项目:国家自然科学基金(编号:62173049、62273060);湖北省教育厅科学研究计划资助项目(编号:D20211302)。
作者简介:李志良(1999—),男,湖北洪湖人,硕士研究生,研究方向为深度学习与目标检测。E-mail:2022710652@yangtzeu.edu.cn。
通信作者:李梦霞,博士,副教授,硕士生导师,研究方向为油气田软件开发、最优化理论与算法。E-mail:limengxia@yangtzeu.edu.cn。
更新日期/Last Update: 2024-07-20