[1]杨淑婷,李季,刘正予,等.面向水稻杂草识别的高精度图像分类算法[J].江苏农业学报,2025,(08):1538-1552.[doi:doi:10.3969/j.issn.1000-4440.2025.08.010]
　YANG Shuting,LI Ji,LIU Zhengyu,et al.High-precision image classification algorithm for recognition of rice weed[J].,2025,(08):1538-1552.[doi:doi:10.3969/j.issn.1000-4440.2025.08.010]
点击复制

面向水稻杂草识别的高精度图像分类算法()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年08期
页码:
1538-1552
栏目:
农业信息工程
出版日期:
2025-08-31

文章信息/Info

Title:
High-precision image classification algorithm for recognition of rice weed
作者:
杨淑婷1; 2; 李季1; 刘正予3; 马聪1; 王蓉4
(1.宁夏农林科学院农业经济与信息技术研究所,宁夏银川750002；2.宁夏数智农业工程技术研究中心,宁夏银川750002；3.南京理工大学计算机科学与工程学院,江苏南京210018；4.农业农村部农产品质量安全监督检验测试中心<银川>,宁夏银川750002)
Author(s):
YANG Shuting1; 2; LI Ji1; LIU Zhengyu3; MA Cong1; WANG Rong4
(1.Institute of Agricultural Economics and Information Technology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China;2.Ningxia Digital and Intelligent Agricultural Engineering Technology Research Center, Yinchuan 750002, China;3.School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210018, China;4.Supervision and Testing Center of Agricultural Products Quality and Safety (Yinchuan), Ministry of Agriculture and Rural Affairs, Yinchuan 750002, China)
关键词:
图像识别; 水稻; 深度学习; 卷积神经网络; 图像处理
Keywords:
image recognition; rice; deep learning; convolutional neural network; image processing
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2025.08.010
文献标志码:
A
摘要:
为实现稻田苗期杂草的精准识别与清除,本研究开展了一项系统性的研究工作。通过对稻田实地环境的图像采集与数据整理,构建了一个水稻杂草图像分类数据集。在此基础上,提出了一种创新的高效水稻杂草图像分类算法YOLOv8n-cls-Swift。在图像特征提取阶段,采用SwiftFormer在复杂的田间场景下有效提取水稻植株与杂草的差异化特征。在分类预测阶段,本研究设计了一种高效的加权分类层,使模型能够更加精准地聚焦于区分性强的目标特征区域,显著提升了模型对判别性目标特征的捕捉能力。结果表明,本研究提出的模型能达到一个较高的识别准确率。本研究提出的一种水稻田杂草清除精准施药系统,能够实现稻田杂草的全自动识别与清除,有望在水稻种植的减药增效、环境保护等方面发挥重要作用。
Abstract:
To achieve accurate identification and removal of weeds during the seedling stage in rice fields, this study carried out a systematic study. By collecting and organizing images from real rice field environments, a rice-weed image classification dataset was constructed. Based on this dataset, an innovative and efficient rice-weed image classification algorithm named YOLOv8n-cls-Swift was proposed. During the image feature extraction phase, SwiftFormer was employed to effectively extract discriminative features between rice plants and weeds under complex field conditions. In the classification prediction phase, an efficient weighted classification layer was designed to enable the model to focus more accurately on highly discriminative target feature regions, and significantly enhanced its ability to capture distinguishing characteristics. The results demonstrated that, the proposed model achieved a high recognition accuracy. The precision herbicide application system for rice fields presented in this study can achieve fully automatic identification and removal of weeds, which is expected to play a significant role in reducing pesticide use, improving efficiency, and protecting the environment in rice cultivation.

参考文献/References:

[1]宁运旺,张辉,张永春. 江苏省水稻种植行为的南北差异及其对化肥投入的影响:以苏州、盐城为例[J]. 江苏农业学报,2018,34(3):533-539.
[2]王忠培,谢成军,董伟,等. 基于多维间注意力机制的水稻病害识别模型[J]. 江苏农业学报,2024,40(4):625-635.
[3]ALOM M Z, TAHA T M, YAKOPCIC C, et al. The history began from alexnet: a comprehensive survey on deep learning approaches[J]. arXiv Preprint,2018,DOI:10.48550/arXiv.1803.01164.
[4]苏赋,吕沁,罗仁泽. 基于深度学习的图像分类研究综述[J]. 电信科学,2019,35(11):58-74.
[5]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90.
[6]VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems,2017,30(1): 5999-6009.
[7]DOSOVITSKIY A. An image is worth 16x16 words:transformers for image recognition at scale[J]. arXiv Preprint,2020,DOI:10.48550/arXiv.2010.11929.
[8]LIU Z, LIN Y T, CAO Y, et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision. October 11-17,2021,Montreal,QC,Canada:IEEE,2021.
[9]TOUVRON H, CORD M, JEGOU H. DeiT III:revenge of the ViT[M]. Cham:Springer Nature Switzerland,2022:516-533.
[10]WANG A, CHEN H, LIN Z J, et al. Rep ViT:revisiting mobile CNN from ViT perspective[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-22,2024,Seattle,WA,USA:IEEE,2024.
[11]DENG R L, JIANG Y, TAO M, et al. Deep learning-based automatic detection of productive tillers in rice[J]. Computers and Electronics in Agriculture,2020,177:105703.
[12]孙俊,谭文军,毛罕平,等. 基于改进卷积神经网络的多种植物叶片病害识别[J]. 农业工程学报,2017,33(19):209-215.
[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]桂越,范国华,唐贝贝,等. 基于卷积神经网络的农田杂草与水稻的分类识别[J]. 洛阳理工学院学报(自然科学版),2019,29(1):78-82,93.
[15]杨森森,张昊,兴陆,等. 改进MobileViT网络识别轻量化田间杂草[J]. 农业工程学报,2023,39(9):152-160.
[16] MEHTA S, RASTEGARI M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[J]. arXiv Preprint,2021.DOI:10.48550/arXiv.2110.02178.
[17] RAHIM A, YUAN F, BARABABY J. An ultralytics YOLOv8-based approach for road detection in snowy environments in the arctic region of norway[J]. Computers, Materials & Continua, 2025,83(3):1546-2218.DOI:10.32604/cmc.2025.061575.
[18]SHAKER A, MAAZ M, RASHEED H, et al. SwiftFormer:efficient additive attention for transformer-based real-time mobile vision applications[C]//2023 IEEE/CVF International Conference on Computer Vision. October 1-6,2023,Paris,France:IEEE,2023.
[19]NISHIYAMA T, KUMAGAI A, KAMIYA K, et al. SILU:strategy involving large-scale unlabeled logs for improving malware detector[C]//2020 IEEE Symposium on Computers and Communications. July 7-10,2020.Rennes,France:IEEE,2020:1-7.
[20]FAN Q H, HUANG H B, CHEN M R, et al. RMT:retentive networks meet vision transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-22,2024,Seattle,WA,USA:IEEE,2024:5641-5651.
[21] LI W, WANG X, XIA X, et al. Sepvit:separable vision transformer[J]. arXiv Preprint,2022. DOI:10.48550/arXiv.2203.15380.
[22]GAO Q, HU X Y, HUANG Y H, et al. An improved EfficientFormerv2 network for bone marrow cell classification[C]//2024 5th International Conference on Computer Vision,Image and Deep Learning. April 19-21,2024,Zhuhai,China:IEEE,2024:822-825.
[23]DENG J, DONG W, SOCHER R, et al. ImageNet:a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. June 20-25,2009,Miami,FL,USA:IEEE,2009:248-255.
[24] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft coco:common objects in context[C]//2014 13th European Conference on Computer Vision,September 6-12,2014,Switzerland,Zurich:Springer, 2014: 740-755.
[25] ISLAM K. Recent advances in vision transformer:a survey and outlook of recent work[J]. arXiv Preprint,2022.DOI:10.48550/arXiv.2203.01536.
[26]SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: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.
[27]LI Y H, EL HABIB DAHO M, CONZE P H, et al. A review of deep learning-based information fusion techniques for multimodal medical image classification[J]. Computers in Biology and Medicine,2024,177:108635.
[28]MARMOLEJO-SAUCEDO J A, KOSE U. Numerical grad-cam based explainable convolutional neural network for brain tumor diagnosis[J]. Mobile Networks and Applications,2024,29(1):109-118.

相似文献/References:

[1]王士磊,丁正权,黄海祥.水稻隐性早熟突变体ref早熟性的遗传分析和基因定位[J].江苏农业学报,2016,(04):721.[doi:10.3969/j.issn.100-4440.2016.04.001]
　WANG Shi-lei,DING Zheng-quan,HUANG Hai-xiang.Inheritance and gene mapping of recessive earliness in rice (Oryza sativa L.)[J].,2016,(08):721.[doi:10.3969/j.issn.100-4440.2016.04.001]
[2]王在满,郑乐,张明华,等.不同播种方式对直播水稻倒伏指数和根系生长的影响[J].江苏农业学报,2016,(04):725.[doi:10.3969/j.issn.100-4440.2016.04.002]
　WANG Zai-man,ZHENG Le,ZHANG Ming-hua,et al.Effects of seeding manners on lodging index and root growth of directseeded rice[J].,2016,(08):725.[doi:10.3969/j.issn.100-4440.2016.04.002]
[3]易能,薛延丰,石志琦,等.微囊藻毒素对水稻种子萌发和幼苗生长的胁迫作用[J].江苏农业学报,2016,(04):729.[doi:10.3969/j.issn.100-4440.2016.04.003]
　YI Neng,XUE Yan-feng,SHI Zhi-qi,et al.Inhibitory effect of microcystins on seed germination and seedling growth of rice[J].,2016,(08):729.[doi:10.3969/j.issn.100-4440.2016.04.003]
[4]刘凯,王爱民,严国红,等.一个水稻显性矮秆突变体的遗传特性与降株高能力[J].江苏农业学报,2016,(05):968.[doi:10.3969/j.issn.1000-4440.2016.05.002]
　LIU Kai,WANG Ai-min,YAN Guo-hong,et al.Genetic analysis and plant height reduction of a dominant dwarf mutant of rice[J].,2016,(08):968.[doi:10.3969/j.issn.1000-4440.2016.05.002]
[5]王红,杨镇,裴文琪,等.功能性微生物制剂对镉胁迫下水稻生长及生理特性的影响[J].江苏农业学报,2016,(05):974.[doi:10.3969/j.issn.1000-4440.2016.05.003]
　WANG Hong,YANG Zhen,PEI Wen-qi,et al.Growth and physiological characteristics of cadmium-stressed rice influenced by functional microorganism agent[J].,2016,(08):974.[doi:10.3969/j.issn.1000-4440.2016.05.003]
[6]孙玲,单捷,毛良君,等.基于遥感和Moran's I指数的水稻面积变化空间自相关性研究[J].江苏农业学报,2016,(05):1060.[doi:10.3969/j.issn.1000-4440.2016.05.017]
　SUN Ling,SHAN Jie,MAO Liang-jun,et al.Spatial autocorrelation of changes in paddy rice area based on remote sensing and Moran’s I index[J].,2016,(08):1060.[doi:10.3969/j.issn.1000-4440.2016.05.017]
[7]张晓忆,李卫国,景元书,等.多种光谱指标构建决策树的水稻种植面积提取[J].江苏农业学报,2016,(05):1060.[doi:10.3969/j.issn.1000-4440.2016.05.018]
　ZHANG Xiao-yi,LI Wei-guo,JING Yuan-shu,et al.Extraction of paddy rice area by constructing the decision tree with multiple spectral indices[J].,2016,(08):1060.[doi:10.3969/j.issn.1000-4440.2016.05.018]
[8]裔传灯,李玮,王德荣,等.水稻GW5基因的1212-bp Indel变异对粒形的影响[J].江苏农业学报,2016,(06):1201.[doi:doi:10.3969/j.issn.1000-4440.2016.06.001]
　YI Chuan-deng,LI Wei,WANG De-rong,et al.Effect of 1212-bp Indel variation of gene GW5 on rice grain shape[J].,2016,(08):1201.[doi:doi:10.3969/j.issn.1000-4440.2016.06.001]
[9]刘红江,陈虞雯,张岳芳,等.不同播栽方式对水稻叶片光合特性及产量的影响[J].江苏农业学报,2016,(06):1206.[doi:doi:10.3969/j.issn.1000-4440.2016.06.002]
　LIU Hong-jiang,CHEN Yu-wen,ZHANG Yue-fang,et al.Effects of planting pattern on leaf photosynthetic characteristics and yield of rice[J].,2016,(08):1206.[doi:doi:10.3969/j.issn.1000-4440.2016.06.002]
[10]郭保卫,许轲,魏海燕,等.钵苗机插水稻茎秆的抗倒伏能力[J].江苏农业学报,2016,(06):1280.[doi:doi:10.3969/j.issn.1000-4440.2016.06.014]
　GUO Bao-wei,XU Ke,WEI Hai-yan,et al.Culm lodging resistance characteristics of bowl seedling mechanical-transplanting rice[J].,2016,(08):1280.[doi:doi:10.3969/j.issn.1000-4440.2016.06.014]

备注/Memo

备注/Memo:
收稿日期:2025-04-22基金项目:宁夏自然科学基金项目(2023AAC03411)；宁夏回族自治区重点研发项目(2023BCF01051、2024BBF01013)作者简介:杨淑婷(1984-),女，宁夏盐池人,硕士,助理研究员,研究方向为农业遥感、智能决策技术研究与应用。(E-mail)nxnkyyst@163.com通讯作者:李季,(E-mail)lijinxnky@163.com
更新日期/Last Update: 2025-09-23