|本期目录/Table of Contents|

[1]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):147-156.
 Zeng Lintao,et al.An apple leaf disease detection method based on improved YOLO v8[J].Jiangsu Agricultural Sciences,2025,53(5):147-156.
点击复制

基于改进YOLO v8的苹果叶部病害检测方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第53卷
期数:
2025年第5期
页码:
147-156
栏目:
病害智能检测
出版日期:
2025-03-05

文章信息/Info

Title:
An apple leaf disease detection method based on improved YOLO v8
作者:
曾林涛123马嘉昕123丁羽123许晓东123
1.塔里木大学机械电气化工程学院,新疆阿拉尔 843300; 2.南疆特色农林产物利用与装备兵团重点实验室,新疆阿拉尔 843300; 3.新疆维吾尔自治区教育厅普通高等学校现代农业工程重点实验室,新疆阿拉尔 843300
Author(s):
Zeng Lintaoet al
关键词:
YOLO v8苹果叶部病害目标检测Shuffle AttentionC2f_DCNV2MPDIoU
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
针对苹果叶部病害在自然环境下形态和颜色特征较为复杂、区分度较低等特点,提出一种高效的病害检测模型,为病害的预防与科学化治理提供准确的依据。基于YOLO v8算法,在主干网络(backbone)末端,加入注意力机制Shuffle Attention(SA),根据样本分布特点进行数据增强,引入Mixup、Mosaic、Random等数据增强方法增加特征表达能力,在提高检测性能的同时,不显著增加计算复杂度;在neck末端,使C2f模块与可变形卷积神经网络模块(Deformable Conv V2)相结合,以提升复杂背景下的检测性能,从而提高检测准确度,有效提高模型性能;为克服CIoU损失函数的局限性,采用MPDIoU损失函数,解决CIoU在特定场景下的限制。结果表明,相较于原始YOLO v8算法,本研究算法的平均准确率提升3.5百分点,mAP@0.5 ∶[KG-*3]0.95提升4.6百分点,精确率提升3.6百分点,说明改进的算法在苹果叶部病害检测方面取得有效成果。
Abstract:
-

参考文献/References:

[1]李娜,田云龙,张蕾,等. 中国化肥减量增效行动与技术研究[J/OL]. 农业资源与环境学报,(2024-03-11)[2024-06-09].
[2]王权顺,吕蕾,黄德丰,等. 基于改进YOLO v4算法的苹果叶部病害缺陷检测研究[J]. 中国农机化学报,2022,43(11):182-187.
[3]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.
[4]Sun H N,Xu H W,Liu B,et al. MEAN-SSD:a novel real-time detector for apple leaf diseases using improved light-weight convolutional neural networks[J]. Computers and Electronics in Agriculture,2021,189:106379.
[5]刘斌,徐皓玮,李承泽,等. 基于快照集成卷积神经网络的苹果叶部病害程度识别[J]. 农业机械学报,2022,53(6):286-294.
[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]贾少鹏,高红菊,杭潇. 基于深度学习的农作物病虫害图像识别技术研究进展[J]. 农业机械学报,2019,50(增刊1):313-317.
[8]Deng F,Pu S L,Chen X H,et al. Hyperspectral image classification with capsule network using limited training samples[J]. Sensors,2018,18(9):3153.
[9]龙阳,肖小玲. 基于多注意力机制的苹果叶部病害检测方法[J]. 江苏农业科学,2023,51(23):178-186.
[10]王金鹏,何萌,甄乾广,等. 基于COF-YOLOv 8n的油茶果静、动态检测计数[J]. 农业机械学报,2024,55(4):193-203.
[11]Zhang X H,Li H L,Sun S H,et al. Classification and identification of apple leaf diseases and insect pests based on improved ResNet-50 model[J]. Horticulturae,2023,9(9):1046.
[12]陈佳慧,王晓虹. 改进YOLO v5的无人机航拍图像密集小目标检测算法[J]. 计算机工程与应用,2024,60(3):100-108.
[13]张艳宁,王鹏,张磊,等. 面向无人移动平台的自主进化学习研究进展与展望[J]. 科学通报,2023,68(35):4821-4843.
[14]Huangfu Z M,Li S Q. Lightweight you only look once v8:an upgraded you only look once v8 algorithm for small object identification in unmanned aerial vehicle images[J]. Applied Sciences,2023,13(22):12369.
[15]Yue X,Qi K,Na X Y,et al. Improved YOLO v8-Seg network for instance segmentation of healthy and diseased tomato plants in the growth stage[J]. Agriculture,2023,13(8):1643.
[16]Qian K,Wang S Q,Zhang S J,et al. SiamPKHT:hyperspectral Siamese tracking based on pyramid shuffle attention and knowledge distillation[J]. Sensors,2023,23(23):9554.
[17]陈军,孙丽丽,孟洪兵,等. 融合瓶颈注意力模块的改进YOLO v7织物疵点检测算法[J]. 棉纺织技术,2024,52(3):53-60.
[18]赵宗扬,康杰虎,吴斌,等. 基于FRL-Net的高鲁棒性多尺度小样本轨道入侵异物检测方法研究[J]. 仪器仪表学报,2024,45(1):239-249.
[19]Sharma S,Kumar V,Rana K P S. Automatic oscillations detection and quantification in process control loops using linear predictive coding[J]. Engineering Science and Technology,an International Journal,2020,23(1):123-143.
[20]刘鑫,马本学,李玉洁,等. 基于改进YOLO v7-ByteTrack的干制哈密大枣缺陷检测与计数系统[J]. 农业工程学报,2024,40(3):303-312.
[21]Xie Y H,Yin B,Han X W,et al. Improved YOLO v7-based steel surface defect detection algorithm[J]. Mathematical Biosciences and Engineering,2024,21(1):346-368.
[22]Iqbal J,Munir M A,Mahmood A,et al. Leveraging orientation for weakly supervised object detection with application to firearm localization[J]. Neurocomputing,2021,440:310-320.
[23]刘毅君,何亚凯,吴晓媚,等. 基于改进Faster R-CNN的马铃薯发芽与表面损伤检测方法[J]. 农业机械学报,2024,55(1):371-378.
[24]舒振宇,秦昊. 基于SKNet注意力机制的飞机类型识别算法[J]. 中南民族大学学报(自然科学版),2024,43(1):69-77.
[25]麻斯亮,许勇. 最小点距离的边界框回归损失函数及其应用[J]. 小型微型计算机系统,2024,45(11):2695-2701.
[26]李云红,张蕾涛,李丽敏,等. 基于CycleGAN-IA方法和 M-ConvNext 网络的苹果叶片病害图像识别[J]. 农业机械学报,2024,55(4):204-212.

相似文献/References:

[1]龙阳,肖小玲.基于多注意力机制的苹果叶部病害检测方法[J].江苏农业科学,2023,51(23):178.
 Long Yang,et al.Apple leaf disease recognition method based on multi-attention mechanism[J].Jiangsu Agricultural Sciences,2023,51(5):178.
[2]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.
 Li Zhiliang,et al.Lightweight corn pest recognition method based on enhanced YOLO v8[J].Jiangsu Agricultural Sciences,2024,52(5):196.
[3]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(5):250.
[4]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(5):209.
[5]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(5):221.
[6]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(5):89.
[7]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(5):62.

备注/Memo

备注/Memo:
收稿日期:2024-04-01
基金项目:新疆生产建设兵团第一师阿拉尔市科技计划(编号:2020ZB04)。
作者简介:曾林涛(1996—)男,河南周口人,硕士研究生,研究方向为农业机械化。E-mail:158123794@qq.com。
通信作者:丁羽,硕士,教授,硕士生导师,主要从事农业机械化研究。E-mail:dyandcae@163.com。
更新日期/Last Update: 2025-03-05