|本期目录/Table of Contents|

[1]许爽,杨乐,刘婷.Ghost-MobileNet v2:一种轻量级玉米田杂草识别新模型[J].江苏农业科学,2024,52(20):173-180.
 Xu Shuang,et al.Ghost-MobileNet v2: a new lightweight identification model for weeds in maize field[J].Jiangsu Agricultural Sciences,2024,52(20):173-180.
点击复制

Ghost-MobileNet v2:一种轻量级玉米田杂草识别新模型(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第52卷
期数:
2024年第20期
页码:
173-180
栏目:
杂草智能检测
出版日期:
2024-10-20

文章信息/Info

Title:
Ghost-MobileNet v2: a new lightweight identification model for weeds in maize field
作者:
许爽2杨乐1刘婷1
1.江西农业大学计算机与信息工程学院,江西南昌 330045; 2.江西农业大学软件学院,江西南昌 330045
Author(s):
Xu Shuanget al
关键词:
深度学习玉米杂草Ghost-MobileNet v2注意力机制
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
农田杂草种类繁多、生命力强、危害作物的各个生长周期,对现代化农业生产依旧具有极大的影响。为了协助农业生产中的杂草防治工作,对杂草准确、无损、高效识别,将深度学习与农业结合,利用深度学习技术对玉米田中的杂草进行识别和分类,从而为玉米田杂草治理提供技术支持。针对经典卷积神经网络计算量大、准确率低、训练时间长等问题,提出了一种基于MobileNet v2轻量级网络的玉米田杂草识别新模型Ghost-MobileNet v2。该模型以MobileNet v2为基础,加入Ghost模块强化信息流动、提升特征表达能力;再加入SE-CBAM注意力机制,该注意力机制由SE注意力机制和CBAM注意力机制并联组合而成,在通道和空间2个维度上综合考虑特征的重要性,更全面地捕捉图像特征,从而提升网络的表达能力和泛化能力。试验结果表明,与其他经典的模型和先进的多尺度模型相比,Ghost-MobileNet v2对玉米田杂草有更好的分类效果,平均准确率达到了99.00%,高于原模型的97.58%。通过精确率、召回率、F1分数等3个评价指标,得出Ghost-MobileNet v2具有鲁棒性好、稳定性高、识别率高等特点,将该网络与现实农业生产中玉米田杂草防治工作相结合,可以有效地提高工作效率。
Abstract:
-

参考文献/References:

[1]Al-Gaashani M S A M,Shang F,El-Latif A A A. Ensemble learning of lightweight deep convolutional neural networks for crop disease image detection[J]. Journal of Circuits,Systems and Computers,2023,32(5):2350086.
[2]Chen J,Zhang D,Suzauddola M,et al. Identification of plant disease images via a squeeze-and-excitation MobileNet model and twice transfer learning[J]. IET Image Processing,2021,15:1115-1127.
[3]Senan N,Aamir M,Ibrahim R,et al. An efficient convolutional neural network for paddy leaf disease and pest classification[J]. International Journal of Advanced Computer Science and Applications,2020,11(7):116-122.
[4]Zhu S,Ma W,Lu J,et al. A novel approach for apple leaf disease image segmentation in complex scenes based on two-stage DeepLab v3+ with adaptive loss[J]. Computers and Electronics in Agriculture,2023,204: 107539.
[5]Kim H,Kim D. Deep-learning-based strawberry leaf pest classification for sustainable smart farms[J]. Sustainability,2023,15(10):7931.
[6]Jaiganesh M,SathyaDevi M,Srinivasa Chakravarthy K,et al. Identification of plant species using CNN- Classifier[J]. Journal of Critical Reviews,2020,7(3):923-931.
[7]Bongulwar D M. Identification of fruits using deep learning approach[J]. IOP Conference Series: Materials Science and Engineering,2021,1049(1):012004.
[8]Chavan T R,Nandedkar A V. AgroAVNET for crops and weeds classification: a step forward in automatic farming[J]. Computers & Electronics in Agriculture,2018,154:361-372.
[9]Wagle S A,Harikrishnan R. A deep learning-based approach in classification and validation of tomato leaf disease[J]. TS,2021,38(3):699-709.
[10]Liu Y W,Zhang X,Gao Y X,et al. Improved CNN method for crop pest identification based on transfer learning[J]. Computational Intelligence and Neuroscience,2022(2022):9709648.
[11]尚建伟,蒋红海,喻刚,等. 基于深度学习的杂草识别系统[J]. 软件导刊,2020,19(7):127-130.
[12]彭文,兰玉彬,岳学军,等. 基于深度卷积神经网络的水稻田杂草识别研究[J]. 华南农业大学学报,2020,41(6):75-81.
[13]邓向武,马旭,齐龙,等. 基于卷积神经网络与迁移学习的稻田苗期杂草识别[J]. 农机化研究,2021,43(10):167-171.
[14]Xu Y L,Zhai Y T,Zhao B,et al. Weed recognition for depthwise separable network based on transfer learning[J]. Intelligent Automation & Soft Computing,2021,27(3):669-682.
[15]姚思雨,王磊,张宏文. 基于CNN的棉田杂草识别方法[J]. 石河子大学学报(自然科学版),2023,41(1):21-26.
[16]陈启,陈慈发,邓向武,等. 基于移动端轻量模型的杂草分类方法研究[J]. 中国农机化学报,2022,43(2):163-170.
[17]Sandler M,Howard A,Zhu M,et al. MobileNet v2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2018:4510-4520.
[18]Han K,Wang Y,Tian Q,et al. GhostNet: more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2020:1577-1586.
[19]Zhang T,Zhang Y N,Xin M L,et al. A light-weight network for small insulator and defect detection using UAV imaging based on improved YOLO v5[J]. Sensors,2023,23(11):5249.
[20]Zhang X W,Zhao Z X,Ran L Y,et al. FastICENet: a real-time and accurate semantic segmentation model for aerial remote sensing river ice image[J]. Signal Processing,2023,212:109150.
[21]Zhao Y,Sun C,Xu X,et al. RIC-Net: a plant disease classification model based on the fusion of inception and residual structure and embedded attention mechanism[J]. Computers and Electronics in Agriculture,2022,193:106644.
[22]Wang Y C,Li J D,Chen Z M,et al. Ships’ small target detection based on the CBAM-YOLOX algorithm[J]. Journal of Marine Science and Engineering,2022,10(12):2013.
[23]张会敏,谢泽奇. 基于多尺度注意力卷积神经网络的苹果叶部病害识别方法[J]. 江苏农业科学,2023,51(16):154-161.
[24]Howard A G,Zhu M,Chen B,et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv,2017,1704.04861v1.
[25]He K,Zhang X,Ren S,et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV,USA,2016: 770-778.
[26]Hu J,Shen L,Sun G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE,2018:7132-7141.

相似文献/References:

[1]孙建伟.水涝胁迫对玉米细胞保护酶同工酶的影响[J].江苏农业科学,2013,41(04):85.
[2]刘荣,张卫建,齐华,等.密植型玉米“中单909”高产群体结构特征[J].江苏农业科学,2013,41(05):56.
 Liu Rong,et al.Study on high yield population structure of close planting maize cultivar “Zhongdan 909”[J].Jiangsu Agricultural Sciences,2013,41(20):56.
[3]沈浜凯,肖龙云,冯乃杰,等.黄腐酸和AM真菌对玉米幼苗抗旱性的影响[J].江苏农业科学,2013,41(05):64.
 Shen Bangkai,et al.Effects of fulvic acid and AM fungi on drought resistance of maize seedlings[J].Jiangsu Agricultural Sciences,2013,41(20):64.
[4]张金然,缑艳霞,孙丽鹏.固氮螺菌157对玉米、向日葵的促生长作用[J].江苏农业科学,2014,42(12):116.
 Zhang Jinran,et al.Effects of Azospirillum 157 on growth of maize and sunflower[J].Jiangsu Agricultural Sciences,2014,42(20):116.
[5]白小军,吴燕,牛艳,等.玉米中乙草胺和莠去津残留量GC-MS/MS分析法的建立[J].江苏农业科学,2014,42(11):334.
 Bai Xiaojun,et al().Establishment of GC-MS/MS analysis method of acetochlor and atrazine residues in maize[J].Jiangsu Agricultural Sciences,2014,42(20):334.
[6]邹晓威,王娜,刘芬,等.玉米抗病相关基因在玉米与玉米丝黑穗病菌、玉米黑粉病菌互作过程中的表达差异分析[J].江苏农业科学,2014,42(11):150.
 Zou Xiaowei,et al(0).Different expression of resistance-related genes between Sporisorium reilianum and Ustilago maydis interact with corn[J].Jiangsu Agricultural Sciences,2014,42(20):150.
[7]杨洪兴,陈静,陈艳萍.江苏省玉米机械化生产的发展及育种对策思考[J].江苏农业科学,2014,42(11):116.
 Yang Hongxing,et al().Development and breeding strategy of mechanized production of maize in Jiangsu Province[J].Jiangsu Agricultural Sciences,2014,42(20):116.
[8]张丽妍,霍剑锋,孟繁盛,等.不同肥料、施肥水平及施用方法对玉米产量、性状及效益的影响[J].江苏农业科学,2014,42(11):119.
 Zhang Liyan,et al (9).Effects of different fertilizers,fertilizer levels and fertilizing methods on yield,characters and benefit of maize[J].Jiangsu Agricultural Sciences,2014,42(20):119.
[9]王雷,崔震海,张立军.玉米C4型PEPC全长基因的克隆与表达载体构建[J].江苏农业科学,2014,42(11):26.
 Wang Lei,et al().Cloning and expression vector construction of full-length C4 type PEPC gene in maize[J].Jiangsu Agricultural Sciences,2014,42(20):26.
[10]雷恩,赵光明,刘艳红.不同稀释浓度松土保水剂对玉米营养生长的影响[J].江苏农业科学,2013,41(06):77.
 Lei En,et al.Effect of different dilutions of super absorbent polymer on vegetative growth of maize[J].Jiangsu Agricultural Sciences,2013,41(20):77.
[11]杨琳琳,别书凡,王建坤,等.基于深度学习的玉米植株表型检测方法研究[J].江苏农业科学,2023,51(19):165.
 Yang Linlin,et al.Study on phenotypic detection method for corn plants based on deep learning[J].Jiangsu Agricultural Sciences,2023,51(20):165.
[12]吕伟,宋轩,杨欢.基于深度学习和多源遥感数据的玉米种植面积提取[J].江苏农业科学,2023,51(23):171.
 Lyu Wei,et al.Extraction of maize planting area based on deep learning and multi-source remote sensing data[J].Jiangsu Agricultural Sciences,2023,51(20):171.
[13]贾海峰,王廷超,洪小丽,等.基于双解码机制的田间玉米冠层图像分割及昼夜节律解析[J].江苏农业科学,2023,51(24):184.
 Jia Haifeng,et al.Field maize canopy image segmentation and circadian rhythms analysis based on double decoding mechanism[J].Jiangsu Agricultural Sciences,2023,51(20):184.
[14]张友为,王鑫鑫,范晓飞.基于深度学习的玉米和番茄病虫害检测技术研究进展[J].江苏农业科学,2024,52(10):10.
 Zhang Youwei,et al.Research progress on corn and tomato diseases and pests detection technology based on deep learning[J].Jiangsu Agricultural Sciences,2024,52(20):10.

备注/Memo

备注/Memo:
收稿日期:2023-12-16
基金项目:国家自然科学基金(编号:61862032);江西省自然科学基金(编号:20202BABL202034)。
作者简介:许爽(1998—),男,湖北孝感人,硕士研究生,主要从事农业信息技术研究。E-mail:1078828268@qq.com。
通信作者:杨乐,硕士,副教授,硕士生导师,主要从事农业信息技术、深度学习等研究。E-mail:jxnzhyangle@163.com。
更新日期/Last Update: 2024-10-20