[1]王彩萍,卢雯皎,吴燕.轻量级深度学习模型在草莓病害识别中的应用——以改进MobileNet v3Small为例[J].江苏农业科学,2026,54(4):222-229.
 Wang Caiping,et al.Application of lightweight deep learning models in strawberry disease recognition: taking improved MobileNet v3small as an example[J].Jiangsu Agricultural Sciences,2026,54(4):222-229.
点击复制

轻量级深度学习模型在草莓病害识别中的应用——以改进MobileNet v3Small为例()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第54卷
期数:
2026年第4期
页码:
222-229
栏目:
病害智能检测
出版日期:
2026-02-20

文章信息/Info

Title:
Application of lightweight deep learning models in strawberry disease recognition: taking improved MobileNet v3small as an example
作者:
王彩萍卢雯皎吴燕
江苏农林职业技术学院,江苏句容 212400
Author(s):
Wang Caipinget al
关键词:
MobileNet v3草莓病害数据增强全维动态卷积SimAM模块
Keywords:
-
分类号:
S126;S436.68+4; TP391.41
DOI:
-
文献标志码:
A
摘要:
为解决草莓病害识别中的高准确率和低计算成本问题,特别是在移动设备上实现高效、准确的实时检测,针对传统人工识别方法耗时且准确度受限的问题,选择轻量级深度学习模型MobileNet v3-Small进行改进,借助引入全维动态卷积(ODConv)与SimAM模块的方式,提升模型对于多尺度特征的提取性能。具体而言,在第1个5×5深度可分离卷积层之后加入ODConv以捕捉低级特征如边缘和纹理,并在后续的深度可分离卷积层中继续添加ODConv,增强多尺度特征捕获能力。此外,在模型较深层添加了SimAM模块,该模块被置于最后一个卷积层后但在全局平均池化层前,以有效提升特征质量。试验基于一个包含3 437张训练图片和934张验证图片的数据集进行,覆盖了角斑病、炭疽果腐病等7种草莓病害类型。结果显示,改进后的模型在验证集上的准确率达到94.11%,较基础模型提升3.74百分点,尤其是在灰霉病、叶斑病和果实白粉病分类上的表现尤为突出。混淆矩阵分析结果显示,改进模型明显减少了错误分类数量并提高了正确分类的能力,精确率、召回率以及F1分数等各项评估指标均证明改进措施的有效性。综上所述,本研究通过改进MobileNet v3-Small网络结构实现了草莓病害的高效识别,明显提高了草莓病害识别的精确率。
Abstract:
-

参考文献/References:

[1]何雨霜,王琢,王湘平,等. 深度学习在农作物病害图像识别中的研究进展[J]. 中国农机化学报,2023,44(2):148-155.
[2]姚建斌,张英娜,刘建华. 基于卷积神经网络和迁移学习的小麦病虫害识[J]. 华北水利水电大学学报(自然科学版),2022,43(2):102-108.
[3]刘敏,周丽. 基于多尺度特征融合网络的苹果病害叶片检测[J]. 中国农机化学报,2023,44(8):184-190.
[4]陈伟文,邝祝芳,王忠伟. 基于卷积神经网络的种苗病害识别方法[J]. 中南林业科技大学学报,2022,42(7): 35-43.
[5]熊梦园,詹炜,桂连友,等. 基于ResNet模型的玉米叶片病害检测与识别[J]. 江苏农业科学,2023,51(8):164-170.
[6]黄铝文,郑梁,黄煜,等. 基于多尺度卷积与通道域增强的草莓病害识别方法[J]. 江苏农业科学,2023,51(10): 202-210.
[7]Yu H L,Cheng X H,Chen C C,et al. Apple leaf disease recognition method with improved residual network[J]. Multimedia Tools and Applications,2022,81(6):7759-7782.
[8]Ma L,Guo X L,Zhao S K,et al. Algorithm of strawberry disease recognition based on deep convolutional neural network[J]. Complexity,2021,2021:6683255.
[9]王晶,崔艳荣. 基于改进MobileNet v3-Small模型的草莓病害识别方法 [J]. 江苏农业科学,2024,52(10):225-234.
[10]Howard A G,Zhu M L,Chen B,et al. MobileNets:efficient convolutional neural networks for mobile vision applications [EB/OL]. (2017-04-17)[2023-09-10]. http://arxiv.org/abs/1704.04861.pdf.
[11]Sandler M,Howard A,Zhu M L,et al. MobileNet v2:inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23,2018,Salt Lake City,UT,USA.IEEE,2018:4510-4520.
[12]Hu J,Shen L,Sun G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,Salt Lake City,UT,USA,2018: 7132-7141.
[13]Woo S,Park J,Lee J Y,et al. CBAM:convolutional block attention module[EB/OL].(2018-07-18)[2024-11-11]. https://arxiv.org/abs/1807.06521.
[14]Cao Y,Xu J,Lin S,et al. GCNet:non-local networks meet squeeze-excitation networks and beyond[EB/OL].(2019-04-25)[2024-11-11]. https://arxiv.org/abs/1904.11492.
[15]Wang Q L,Wu B G,Zhu P F,et al. ECA-Net: efficient channel attention for deep convolutional neural networks[EB/OL].(2020-04-07)[2024-11-11]. https://arxiv.org/abs/1910.03151.
[16]Lee H J,Kim H E,Nam H. SRM:a style-based recalibration module for convolutional neural networks[EB/OL].(2019-03-26)[2024-11-11]. https://arxiv.org/pdf/1903.10829.
[17]彭炜烨. 高压传输线路绝缘子缺陷检测方法研究[D]. 沈阳:沈阳理工大学,2024.

相似文献/References:

[1]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(4):187.
[2]张风伟,朱成杰,朱洪波.基于改进MobileNet v3的苹果叶片病害识别方法及移动端应用[J].江苏农业科学,2024,52(7):205.
 Zhang Fengwei,et al.Apple leaf disease recognition method based on improved MobileNet v3 and its mobile terminal application[J].Jiangsu Agricultural Sciences,2024,52(4):205.
[3]王晶,崔艳荣.基于改进MobileNet v3-Small模型的草莓病害识别方法[J].江苏农业科学,2024,52(10):225.
 Wang Jing,et al.Strawberry disease identification method based on improved MobileNet v3-Small model[J].Jiangsu Agricultural Sciences,2024,52(4):225.
[4]郑超杰,李少波,蒲睿强,等.基于轻量化卷积神经网络的番茄叶片病害识别[J].江苏农业科学,2024,52(11):225.
 Zheng Chaojie,et al.Tomato leaf disease recognition based on lightweight convolutional neural network[J].Jiangsu Agricultural Sciences,2024,52(4):225.
[5]李豫晋,沈陆明,何少芳,等.基于改进MobileNet v3的苹果叶片病害识别研究[J].江苏农业科学,2024,52(12):224.
 Li Yujin,et al.Identification of apple leaf diseases based on improved MobileNet v3[J].Jiangsu Agricultural Sciences,2024,52(4):224.
[6]周江龙,王天一,李论,等.基于深度学习的轻量化农作物叶片病害识别模型[J].江苏农业科学,2024,52(16):230.
 Zhou Jianglong,et al.A lightweight model for crop leaf disease identification based on deep learning[J].Jiangsu Agricultural Sciences,2024,52(4):230.
[7]董虎胜,鲜学丰,孙逊,等.基于多阶段特征融合的MobileNet v3ULAM茶叶病害识别[J].江苏农业科学,2025,53(15):200.
 Dong Husheng,et al.Identification of tea leaf disease based on MobileNet v3ULAM with multistage feature fusion[J].Jiangsu Agricultural Sciences,2025,53(4):200.
[8]陈雪,谭峰,宁韶瞳,等.基于轻量级网络的玉米田间杂草识别方法[J].江苏农业科学,2025,53(20):194.
 Chen Xue,et al.A weed identification method for corn field based on lightweight network[J].Jiangsu Agricultural Sciences,2025,53(4):194.
[9]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(4):262.
[10]李艳,戴家豪,戴庆瑜.基于YOLOStrawberry的草莓病害检测模型[J].江苏农业科学,2025,53(20):272.
 Li Yan,et al.A detection model for strawberry diseases based on YOLOstrawberry[J].Jiangsu Agricultural Sciences,2025,53(4):272.

备注/Memo

备注/Memo:
收稿日期:2024-11-12
基金项目:江苏农林职业技术学院科技项目(编号:2022kj38);江苏省高校自然科学基金(编号:23KJB180007)。
作者简介:王彩萍(1982—),女,山东烟台人,硕士,实验师,主要从事大数据、图像识别等方面的研究。E-mail:23215542@qq.com。
更新日期/Last Update: 2026-02-20