[1]曾晏林,贺壹婷,蔺瑶,等.基于BCE-YOLOv5的苹果叶部病害检测方法[J].江苏农业科学,2023,51(15):155-163.
　Zeng Yanlin,et al.An apple leaf disease detection method based on BCE-YOLOv5[J].Jiangsu Agricultural Sciences,2023,51(15):155-163.
点击复制

基于BCE-YOLOv5的苹果叶部病害检测方法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第15期
页码:
155-163
栏目:
农业工程与信息技术
出版日期:
2023-08-05

文章信息/Info

Title:
An apple leaf disease detection method based on BCE-YOLOv5
作者:
曾晏林; 贺壹婷; 蔺瑶; 费加杰; 黎强; 杨毅
云南农业大学大数据学院，云南昆明 650201
Author(s):
Zeng Yanlin; et al
关键词:
苹果; 叶片病害; 识别; 注意力机制; YOLOv5; BotNet; ConvNeXt; CBAM; α-IoU
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对自然环境中，人工目视解译苹果叶部病害耗时耗力、人为主观因素强的问题。本研究提出了一种融合自注意力机制和Transformer模块的目标检测算法——BCE-YOLOv5，实现对自然环境下对苹果叶片病虫害的自动识别与检测。该算法首先使用BotNet、ConvNeXt模块分别替换Backbone网络和Neck网络的CSP结构，增加自注意力机制对目标的特征提取能力。通过将改进的CBAM引入YOLOv5的特征融合网络之后，使注意力机制对特征融合信息更加地关注。最后，用α-IoU损失函数替换IoU损失函数，使得网络在模型训练过程中收敛的更加稳定。BCE-YOLOv5算法在传统算法YOLOv5基础上平均精准率均值提升了2.9百分点，并且改进后的算法的模型大小和计算量较传统算法分别减小了0.2 M和0.9 GFLOPs。平均精度均值比YOLOv4s、YOLOv6s、YOLOx-s和YOLOv7模型分别高2.5、1.3、3.5、2.2百分点。该方法能快速准确识别苹果叶部病害，为苹果种植过程中提供智能化管理做参考。
Abstract:
-

参考文献/References:

［1］刘斌，贾润昌，朱先语，等. 面向移动端的苹果叶部病虫害轻量级识别模型［J］. 农业工程学报，2022，38(6)：130-139.
［2］龙满生，欧阳春娟，刘欢，等. 基于卷积神经网络与迁移学习的油茶病害图像识别［J］. 农业工程学报，2018，34(18)：194-201.
［3］于洪涛，袁明新，王琪，等. 基于VGG-F动态学习模型的苹果病虫害识别［J］. 科学技术与工程，2019，19(32)：249-253.
［4］王云露，吴杰芳，兰鹏，等. 基于改进Faster R-CNN的苹果叶部病害识别方法［J］. 林业工程学报，2022，7(1)：153-159.
［5］田靓靓. 基于SSD网络的苹果叶片病害检测方法研究［D］. 杨凌：西北农林科技大学，2022.
［6］Di J，Li Q. A method of detecting apple leaf diseases based on improved convolutional neural network［J］. PLoS One，2022，17(2)：e0262629.
［7］Tian Y，Yang G，Wang Z，et al. Detection of apple lesions in orchards based on deep learning methods of cyclegan and yolov3-dense［J］. Journal of Sensors，2019，2019.
［8］Mathew M P，Mahesh T Y. Determining the region of apple leaf affected by disease using YOLO V3［C］//2021 International Conference on Communication，Control and Information Sciences (ICCISc). IduKKi，India，2021：1-4.
［9］Li J，Zhu X，Jia R，et al. Apple-YOLO：a novel mobile terminal detector based on YOLOv5 for early apple leaf diseases［C］//2022 IEEE 46th Annual Computers，Software，and Applications Conference (COMPSAC). Los Alamitos，CA,USA，2022：352-361.
［10］Wang Y L，Sun F G，Wang Z J，et al. Apple leaf disease identification method based on improved YoloV5［M］//Sun J D，Wang Y，Huo M Y，et al. Signal and information processing，networking and computers. Singapore：Springer，2023：1246-1252.
［11］Kuznetsova A，Maleva T，Soloviev V. YOLOv5 versus YOLOv3 for apple detection［M］//Kravets A G，Bolshakov A A，Shcherbakov M.Cyber-physical systems：modelling and intelligent control. Cham：Springer，2021：349-358.
［12］Chen Z，Wu R，Lin Y，et al. Plant disease recognition model based on improved YOLOv5［J］. Agronomy，2022，12(2)：365.
［13］晁晓菲，池敬柯，张继伟，等. 基于PSA-YOLO网络的苹果叶片病斑检测［J］. 农业机械学报，2022，53(8)：329-336.
［14］邸洁，曲建华.基于Tiny-YOLO的苹果叶部病害检测［J］. 山东师范大学学报(自然科学版)，2020，35(1)：78-83.
［15］Polder G，Blok P M，van Daalen J T，et al. Early disease detection in apple and grape using deep learning on a smart-camera［C］//Proceedings of the European Conference on Agricultural Engineering. EurAgEng，Cranfield，2021：51-56.
［16］Liu B，Zhang Y，He D J，et al. Identification of apple leaf diseases based on deep convolutional neural networks［J］. Symmetry，2017，10(1)：11.
［17］Srinivas A，Lin T Y，Parmar N，et al. Bottleneck transformers for visual recognition［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Kuala Lumpur，2021：16519-16529.
［18］Liu Z，Mao H Z，Wu C Y，et al. A convnet for the 2020s［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans，2022：11976-11986.
［19］黄文博，黄钰翔，姚远，等. 融合注意力的ConvNeXt视网膜病变自动分级［J］. 光学精密工程，2022，30(17)：2147-2154.
［20］Zhang Z，Lu X，Cao G，et al. ViT-YOLO：Transformer-based YOLO for object detection［C］//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021：2799-2808.
［21］Liu Y，He G，Wang Z，et al. NRT-YOLO：Improved YOLOv5 based on nested residual transformer for tiny remote sensing object detection［J］. Sensors，2022，22(13)：4953.
［22］Woo S，Park J，Lee J Y，et al. Cbam：Convolutional block attention module［C］//Proceedings of the European Conference on Computer Vision (ECCV). Munich，2018：3-19.
［23］Wang Q L，Wu B G，Zhu P F，et al. Eca-net：Efficient channel attention for deep convolutional neural networks［C］//2020 IEEE Conference on Computer Vision and Pattern Recognition. Seattle，2020.
［24］Wang Q，Wu B，Zhu P，et al. Supplementary material for ‘ECA-Net：efficient channel attention for deep convolutional neural networks［C］//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition，IEEE，Seattle，WA，USA. 2020：13-19.
［25］Li X，Xia H，Lu L. ECA-CBAM：Classification of diabetic retinopathy：classification of diabetic retinopathy by cross-combined attention mechanism［C］//2022 the 6th International Conference on Innovation in Artificial Intelligence (ICIAI). 2022：78-82.
［26］He J B，Erfani S M，Ma X J，et al. Alpha -IoU：a family of power intersection over union losses for bounding box regression［J］. Advances in Neural Information Processing Systems，2021，34：20230-20242.
［27］Bochkovskiy A，Wang C Y，Liao H Y M. Yolov4：Optimal speed and accuracy of object detection［EB/OL］. ［2022-12-12］.https://arxiv.org/abs/2004.10934.
［28］Ge Z，Liu S T，Wang F，et al. Yolox：Exceeding yolo series in 2021［EB/OL］. ［2022-12-12］. https://arxiv.org/abs/2107.08430.
［29］Li C，Li L，Jiang H，et al. YOLOv6：A single-stage object detection framework for industrial applications［EB/OL］. ［2022-12-12］.https://https://arxiv.org/abs/2209.02976.
［30］Wang C Y，Bochkovskiy A，Liao H Y M. YOLOv7：Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［EB/OL］. ［2022-12-12］. http://arXiv.ORG/ABS/2207.02696.

相似文献/References:

[1]贾永华,李晓龙,牛锐敏,等.叶面喷锌对苹果叶片生长及产量品质的影响[J].江苏农业科学,2014,42(12):218.
　Jia Yonghua,et al.Effects of spraying zinc on leaves on leaf growth ， yield and quality of apple[J].Jiangsu Agricultural Sciences,2014,42(15):218.
[2]里程辉,刘志,王宏,等.不同化学疏花剂对岳帅苹果疏花疏果及果实品质的影响[J].江苏农业科学,2014,42(11):180.
　Li Chenghui,et al(80).Effects of different chemical flower thinners on flower thinning and fruit quality of apple “Yueshuai”[J].Jiangsu Agricultural Sciences,2014,42(15):180.
[3]王贵平,王金政.苹果抗逆性研究进展与鉴定方法[J].江苏农业科学,2013,41(07):151.
　Wang Guiping,et al.Research progress and identification method of stress resistance of apple trees[J].Jiangsu Agricultural Sciences,2013,41(15):151.
[4]李敏,厉恩茂,李壮,等.氨基酸钙叶面微肥对苹果缺素症的矫正及果实品质的影响[J].江苏农业科学,2013,41(11):180.
　Li Min,et al.Effects of calcium amino acid foliar fertilizer on apple element deficiency disease and fruit quality[J].Jiangsu Agricultural Sciences,2013,41(15):180.
[5]王贵平,王金政,薛晓敏,等.晚秋叶施高浓度尿素对苹果落叶及贮藏氮素的影响[J].江苏农业科学,2014,42(01):140.
　Wang Guiping,et al.Effects of high concentrations of foliar applied urea on defoliation and nitrogen storage of apple in late autumn[J].Jiangsu Agricultural Sciences,2014,42(15):140.
[6]宋哲,王宏,于年文,等.间伐、控冠处理对乔化凉香苹果树光合速率和果实产质量的影响[J].江苏农业科学,2016,44(05):290.
　Song Zhe,et al.Effects of thinning and crown control on photosynthesis and fruit yield and quality of Liangxiang apple trees[J].Jiangsu Agricultural Sciences,2016,44(15):290.
[7]黄金凤,王冬梅,闫忠业,等.苹果遗传图谱的构建与QTL定位研究进展[J].江苏农业科学,2016,44(02):4.
　Huang Jinfeng,et al.Construction of genetic map of apple and research progress of QTL localization[J].Jiangsu Agricultural Sciences,2016,44(15):4.
[8]苏律,宋俊霞,胡同乐,等.铁肥不同施用方式对苹果缺铁黄化病的矫正效果[J].江苏农业科学,2016,44(01):188.
　Su Lü,et al.Corrective effect of iron fertilizer with different fertilization methods on iron chlorosis of apple tree[J].Jiangsu Agricultural Sciences,2016,44(15):188.
[9]李静,宋飞虎,浦宏杰,等.苹果控制排湿压力微波干燥模型研究[J].江苏农业科学,2015,43(11):529.
　Li Jing,et al.Study on mathematical modeling of apple microwave drying under different moisture pressures[J].Jiangsu Agricultural Sciences,2015,43(15):529.
[10]廖春丽,王衡,李亚平,等.L-半胱氨酸及金属离子对马铃薯、苹果、甘薯多酚氧化酶活性的影响[J].江苏农业科学,2015,43(11):375.
　Liao Chunli,et al.Effects of L-cysteine and metal ions on activity of polyphenol oxidase from potato，apple and sweet potato[J].Jiangsu Agricultural Sciences,2015,43(15):375.
[11]王浩宇,崔艳荣.基于改进ShuffleNet v2模型的苹果叶片病害识别方法[J].江苏农业科学,2024,52(13):214.
　Wang Haoyu,et al.Apple leaf disease identification method based on improved ShuffleNet v2 model[J].Jiangsu Agricultural Sciences,2024,52(15):214.
[12]黄贻望,王国帅,毛志,等.KMeans++与注意力机制融合的苹果叶片病害识别方法[J].江苏农业科学,2024,52(20):190.
　Huang Yiwang,et al.Identification of apple leaf diseases in complex environments through integration of KMeans++ and attention mechanisms[J].Jiangsu Agricultural Sciences,2024,52(15):190.

备注/Memo

备注/Memo:
收稿日期：2023-01-04
基金项目：云南省重大科技专项(编号：202002AE09001002)。
作者简介：曾晏林(1993—)，男，四川广安人，硕士研究生，主要从事计算机视觉方面研究。E-mail：786823791@qq.com。
通信作者：杨毅，教授，主要从事农业信息化方面研究。E-mail：yyang66@126.com。
更新日期/Last Update: 2023-08-05