1.昆明理工大学信息工程与自动化学院,昆明 650504
2.昆明理工大学信息化建设管理中心,昆明 650504
3.昆明理工大学-曙光信息产业股份有限公司AI联合研究中心,昆明 650504
李亚,E-mail:59515091@qq.com
朱贵富,E-mail:zhuguifu@kust.edu.cn
收稿:2024-12-24,
纸质出版:2025-07-05
移动端阅览
李亚,陈晓东,王海瑞,等.基于优化MobileViT模型的轻量化田间杂草识别[J].华中农业大学学报,2025,44(4):192‐203.
LI Ya,CHEN Xiaodong,WANG Hairui,et al.Lightweighted identification of weed in field based on optimized MobileViT model[J].Journal of Huazhong Agricultural University,2025,44(04):192-203.
李亚,陈晓东,王海瑞,等.基于优化MobileViT模型的轻量化田间杂草识别[J].华中农业大学学报,2025,44(4):192‐203. DOI: 10.13300/j.cnki.hnlkxb.2025.04.019.
LI Ya,CHEN Xiaodong,WANG Hairui,et al.Lightweighted identification of weed in field based on optimized MobileViT model[J].Journal of Huazhong Agricultural University,2025,44(04):192-203. DOI: 10.13300/j.cnki.hnlkxb.2025.04.019.
针对农业环境中杂草与作物幼苗的识别挑战,提出一种基于优化MobileViT模型的轻量化识别方法。首先引入SimAM注意力机制,增强模型对特征的注意力能力,使用SCConv卷积模块减少卷积神经网络中特征的空间和通道冗余来降低计算成本和模型存储,同时提高卷积模块性能;提出联合使用Label Smoothing Loss和Cross Entropy Loss的损失函数策略,提升模型的泛化性能,降低过拟合风险,并加速模型的收敛过程。选取12种田间常见作物幼苗与杂草图像作为训练数据集评估改进模型MobileViT-SS的性能,结果显示,改进模型的平均识别准确率、精确度、召回率、
F
1
分数分别达到95.91%、95.97%、95.46%、95.69%,均优于当前广泛使用的深度神经网络模型VGG-16、ResNet-18和MobileNetv3。结果表明,改进模型MobileViT-SS能够精准、快速区分多种形态相似的杂草与作物幼苗。
A lightweighted method based on the optimized MobileViT model was proposed to solve the challenges in identifying weeds from crop seedlings in agricultural environments.SimAM attention mechanism was introduced to enhance the model's ability to pay attention to features.SCConv convolution module was used to reduce the spatial and channel redundancy of features in convolutional neural networks to lower computational costs and model storage, while improving the performance of the convolution module.A loss function strategy combining Label Smoothing Loss and Cross Entropy Loss was proposed to improve the generalization performance of the model, reduce the risk of overfitting, and accelerate the convergence process of the model.Images of 12 common crop seedlings and weeds in the field were used as the training dataset to evaluate the performance of the improved model MobileViT-SS.The results showed that the average recognition accuracy, precision, recall rate, and the
F
1
score of the improved model reached 95.91%, 95.97%, 95.46%, and 95.69%, respectively, all of which were superior to that in the widely used deep neural network models including VGG-16, ResNet-18, and MobileNetv3.It is indicated that the improved model MobileViT-SS can accurately and quickly distinguish various weeds from crop seedlings with similar morphology.It will provide technical reference for the identification of weeds from crop seedlings with similar morphology.
MACHLEB J,PETEINATOS G G,KOLLENDA B L,et al.Sensor-based mechanical weed control:present state and prospects[J/OL].Computers and electronics in agriculture,2020,176:105638[2024-12-24]. https://doi.org/10.1016/j.compag.2020.105638.
胡炼,刘海龙,何杰,等.智能除草机器人研究现状与展望[J].华南农业大学学报,2023,44(1):34-42.HU L,LIU H L,HE J,et al.Research progress and prospect of intelligent weeding robot[J].Journal of South China Agricultural University,2023,44(1):34-42 (in Chinese with English abstract) .
CHEN D,LU Y Z,LI Z J,et al.Performance evaluation of deep transfer learning on multi-class identification of common weed species in cotton production systems[J/OL].Computers and electronics in agriculture,2022,198:107091[2024-12-24].https://doi.org/10.1016/j.compag.2022.107091.
HASAN A S M M,SOHEL F,DIEPEVEEN D,et al.A survey of deep learning techniques for weed detection from images[J/OL].Computers and electronics in agriculture,2021,184:106067[2024-12-24].https://doi.org/10.1016/j.compag.2021.106067.
GAO J F,FRENCH A P,POUND M P,et al.Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields[J/OL].Plant methods,2020,16:29[2024-12-24].https://doi.org/10.1186/s13007-020-00570-z.
吴兰兰,徐恺,熊利荣.基于视觉注意模型的苗期油菜田间杂草检测[J].华中农业大学学报,2018,37(2):96-102.WU L L,XU K,XIONG L R.Detecting weed in seedling rapeseed oil field based on visual-attention model[J].Journal of Huazhong Agricultural University,2018,37(2):96-102 (in Chinese with English abstract) .
疏雅丽,张国伟,王博,等.基于深层连接注意力机制的田间杂草识别方法[J].计算机工程与应用,2022,58(6):271-277.SHU Y L,ZHANG G W,WANG B,et al.Field weed identification method based on deep connection attention mechanism[J].Computer engineering and applications,2022,58(6):271-277 (in Chinese with English abstract) .
ZHUANG J Y,LI X H,BAGAVATHIANNAN M,et al.Evaluation of different deep convolutional neural networks for detection of broadleaf weed seedlings in wheat[J].Pest management science,2022,78(2):521-529.
LUO T Y,ZHAO J Y,GU Y J,et al.Classification of weed seeds based on visual images and deep learning[J].Information processing in agriculture,2023,10(1):40-51.
满超,饶元,张敬尧,等.基于改进Inception网络的复杂环境下小样本黄瓜叶片病害识别[J].华中农业大学学报,2023,42(3):152-160.MAN C,RAO Y,ZHANG J Y,et al.Recognition of cucumber leaf disease with small samples in complex environment based on improved Inception network[J].Journal of Huazhong Agricultural University,2023,42(3):152-160 (in Chinese with English abstract) .
ABADE A,FERREIRA P A,DE BARROS VIDAL F.Plant diseases recognition on images using convolutional neural networks:a systematic review[J/OL].Computers and electronics in agriculture,2021,185:106125[2024-12-24].https://doi.org/10.1016/j.compag.2021.106125.
金小俊,孙艳霞,于佳琳,等.基于深度学习与图像处理的蔬菜苗期杂草识别方法[J].吉林大学学报(工学版),2023,53(8):2421-2429.JIN X J,SUN Y X,YU J L,et al.Weed recognition in vegetable at seedling stage based on deep learning and image processing[J].Journal of Jilin University (engineering and technology edition),2023,53(8):2421-2429 (in Chinese with English abstract) .
YU J L,SHARPE S M,SCHUMANN A W,et al.Deep learning for image-based weed detection in turfgrass[J].European journal of agronomy,2019,104:78-84.
GARCÍA-NAVARRETE O L,CORREA-GUIMARAES A,NAVAS-GRACIA L M.Application of convolutional neural networks in weed detection and identification:a systematic review[J/OL].Agriculture,2024,14(4):568[2024-12-24].https://doi.org/10.3390/agriculture14040568.
OLSEN A,KONOVALOV D A,PHILIPPA B,et al.DeepWeeds:a multiclass weed species image dataset for deep learning[J/OL].Scientific reports,2019,9(1):2058[2024-12-24].https://doi.org/10.1038/s41598-018-38343-3.
蔡竹轩,蔡雨霖,曾凡国,等.基于改进YOLOv5l的田间水稻稻穗识别[J].华南农业大学学报,2024,45(1):108-115.CAI Z X,CAI Y L,ZENG F G,et al.Rice panicle recognition in field based on improved YOLOv5l model[J].Journal of South China Agricultural University,2024,45(1):108-115 (in Chinese with English abstract) .
张乐,金秀,傅雷扬,等.基于Faster R-CNN深度网络的油菜田间杂草识别方法[J].激光与光电子学进展,2020,57(2):21508.ZHANG L,JIN X,FU L Y,et al.Recognition method for weeds in rapeseed field based on faster R-CNN deep network[J].Laser & optoelectronics progress,2020,57(2):21508 (in Chinese with English abstract) .
孙俊,朱伟栋,罗元秋,等.基于改进MobileNet-V2的田间农作物叶片病害识别[J].农业工程学报,2021,37(22):161-169.SUN J,ZHU W D,LUO Y Q,et al.Recognizing the diseases of crop leaves in fields using improved MobileNet-V2[J].Transactions of the CSAE,2021,37(22):161-169 (in Chinese with English abstract) .
郭小燕,于帅卿,沈航驰,等.基于全局特征提取的农作物病害识别模型[J].农业机械学报,2022,53(12):301-307.GUO X Y,YU S Q,SHEN H C,et al.Deep learning network for crop disease recognition with global feature extraction[J].Transactions of the CSAM,2022,53(12):301-307 (in Chinese with English abstract) .
刘志,翟瑞芳,彭万伟,等.融合注意力机制的Cascade R-CNN田间害虫检测方法[J].华中农业大学学报,2023,42(3):133-142.LIU Z,ZHAI R F,PENG W W,et al.Field pest detection method based on improved Cascade R-CNN by incorporating attention mechanism[J].Journal of Huazhong Agricultural University,2023,42(3):133-142 (in Chinese with English abstract) .
CHEN Y J,WU Z N,ZHAO B,et al.Weed and corn seedling detection in field based on multi feature fusion and support vector machine[J/OL].Sensors,2020,21(1):212[2024-12-24].https://doi.org/10.3390/s21010212.
GUO M H,XU T X,LIU J J,et al.Attention mechanisms in computer vision:a survey[J].Computational visual media,2022,8(3):331-368.
刘文婷,卢新明.基于计算机视觉的Transformer研究进展[J].计算机工程与应用,2022,58(6):1-16.LIU W T,LU X M.Research progress of transformer based on computer vision[J].Computer engineering and applications,2022,58(6):1-16 (in Chinese with English abstract) .
田永林,王雨桐,王建功,等.视觉Transformer研究的关键问题:现状及展望[J].自动化学报,2022,48(4):957-979.TIAN Y L,WANG Y T,WANG J G,et al.Key problems and progress of vision transformers:the state of the art and prospects[J].Acta automatica sinica,2022,48(4):957-979 (in Chinese with English abstract) .
LIU Y,ZHANG Y,WANG Y X,et al.A survey of visual transformers[J].IEEE transactions on neural networks and learning systems,2024,35(6):7478-7498.
李健,王晨,马振宇,等.MobileNet-CAL:基于迁移学习和注意力机制的番茄病虫害分类方法[J/OL].吉林大学学报(工学版),2023:1-9[2024-12-24].https://doi.org/10.13229/j.cnki.jdxbgxb.20230828.LI J,WANG C,MA Z Y,et al.MobileNet-CAL:a classification method of tomato diseases and pests based on transfer learning and attention mechanism[J/OL].Journal of Jilin University(engineering and technology edition),2023:1-9[2024-12-24].https://doi.org/10.13229/j.cnki.jdxbgxb.20230828 (in Chinese with English abstract) .
亢洁,刘港,郭国法.基于多尺度融合模块和特征 增强的杂草检测方法[J].农业机械学报,2022,53(4):254-260.KANG J,LIU G,GUO G F.Weed detection based on multi-scale fusion module and feature enhancement[J].Transactions of the CSAM,2022,53(4):254-260 (in Chinese with English abstract) .
徐艳蕾,何润,翟钰婷,等.基于轻量卷积网络的田间自然环境杂草识别方法[J].吉林大学学报(工学版),2021,51(6):2304-2312.XU Y L,HE R,ZHAI Y T,et al.Weed identification method based on deep transfer learning in field natural environment[J].Journal of Jilin University (engineering and technology edition),2021,51(6):2304-2312 (in Chinese with English abstract) .
杨志凯,扶兰兰,唐灿,等.基于MobileViT模型的小麦收获机喂入密度分类方法[J].农业机械学报,2023,54(S1):172-180.YANG Z K,FU L L,TANG C,et al.Classification method of feeding density of wheat harvester based on MobileViT model[J].Transactions of the CSAM,2023,54(S1):172-180 (in Chinese with English abstract) .
JIANG H H,ZHANG C Y,QIAO Y L,et al.CNN feature based graph convolutional network for weed and crop recognition in smart farming[J/OL].Computers and electronics in agriculture,2020,174:105450[2024-12-24].https://doi.org/10.1016/j.compag.2020.105450.
SENGUPTA A,YE Y T,WANG R,et al.Going deeper in spiking neural networks:VGG and residual architectures[J/OL].Frontiers in neuroscience,2019,13:95[2024-12-24].https://doi.org/10.3389/fnins.2019.00095.
HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2016 I EEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30,2016 ,Las Vegas,NV,USA.Las Vegas: IEEE,2016:770-778.
ZHANG X Y,ZHOU X Y,LIN M X,et al.ShuffleNet:an extremely efficient convolutional neural network for mobile devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23,2018 ,Salt Lake City,UT,USA.Salt Lake City: IEEE,2018:6848-6856.
Tan M, Le Q.Efficientnet: Rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. June 9-15, 2019 , Long Beach, California, USA.New York: PMLR, 2019: 6105-6114.
HOWARD A,SANDLER M,CHEN B,et al.Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).October 27-November 2,2019.Seoul,Korea.Seoul: IEEE,2019:1314-1324.
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621