An improved YOLOv8n-based model for identifying weeds and seedling of maize

LU Jing′ao; GU Wenhui; ZHENG Jiye; WEI Guojian; SHI Song; ZHENG Shiling; ZHANG Xiaoyan

doi:10.13300/j.cnki.hnlkxb.2026.03.004

您当前的位置：

首页 >

文章列表页 >

An improved YOLOv8n-based model for identifying weeds and seedling of maize

Agricultural artificial intelligence | 更新时间：2026-11-05

- An improved YOLOv8n-based model for identifying weeds and seedling of maize
- Journal of Huazhong Agricultural University Vol. 45, Issue 3, Pages: 45-55(2026)
- 作者机构：
  
  1.聊城大学物理科学与信息工程学院，聊城 252000
  2.山东省农业科学院农业信息与经济研究所，济南 250100
  3.山东省农业机械科学研究院，济南 250100
- 作者简介：
- 基金信息：
- DOI：10.13300/j.cnki.hnlkxb.2026.03.004
  CLC： TP391.4;S451
- Received：05 October 2025，
  
  Published：25 May 2026
- 稿件说明：
移动端阅览
路京奥，顾文辉，郑纪业，等.基于YOLOv8n改进的玉米幼苗杂草识别模型［J］.华中农业大学学报，2026，45（3）：45‐55.

LU Jing′ao,GU Wenhui,ZHENG Jiye,et al.An improved YOLOv8n-based model for identifying weeds and seedling of maize[J].Journal of Huazhong Agricultural University,2026,45(03):45-55.
路京奥，顾文辉，郑纪业，等.基于YOLOv8n改进的玉米幼苗杂草识别模型［J］.华中农业大学学报，2026，45（3）：45‐55. DOI： 10.13300/j.cnki.hnlkxb.2026.03.004.

LU Jing′ao,GU Wenhui,ZHENG Jiye,et al.An improved YOLOv8n-based model for identifying weeds and seedling of maize[J].Journal of Huazhong Agricultural University,2026,45(03):45-55. DOI： 10.13300/j.cnki.hnlkxb.2026.03.004.

摘要

为有效控制玉米幼苗杂草危害，提升杂草识别精度，并适配移动端部署需求，提出一种轻量化YOLOv8n-DSSW模型。该模型引入C2f_Dual模块，实现初步轻量化；使用SPDConv模块增强模型对小目标检测和低分辨率图像的感知能力，并进一步实现轻量化；引入SPPELAN模块增强多尺度特征感知能力；回归损失函数使用Inner-WIoU，辅助框优化边界框定位精度并合理分配模型对不同质量锚框的权重，整体提升识别精度与鲁棒性。结果显示，改进后模型在玉米幼苗和杂草识别任务中，精确率、召回率、平均精确率分别提升3.4、1.9、2.4百分点，权重轻量15.9%，浮点运算速度减少14.8%。结果表明，该模型在杂草特征弱、杂草与玉米重叠、形态相似等复杂田间环境下仍保持较高识别性能，模型大小与计算效率适合在移动装备端部署。

Abstract

A lightweight model named as YOLOv8n-DSSW was developed based on YOLOv8n to effectively control the damage of weeds in maize seedlings， improve the accuracy of identifying weeds， and meet the requirements for mobile deployment.The C2f_Dual module was integrated to achieve initial lightweight.The SPDConv module was used to enhance the capability of identification for small targets and low-resolution images while further reducing the complexity of model.The SPPELAN module was incorporated to strengthen the perception of multi-scale feature.The regression loss function used Inner WIOU to assist in optimizing the accuracy of bounding box localization and allocating weights to anchor boxes of different qualities， thereby overall improving the accuracy and robustness of identification.The results showed that the proposed model achieved an increase of 3.4 percentage points in precision， 1.9 percentage points in recall， and 2.4 percentage points in mean average precision （mAP） in identifying weeds and seedling of maize.The weight of model was reduced by 15.9% and floating-point operations （FLOPs） decreased by 14.8%.This model maintained high performance of identification in complex field environments including weak features of weeds， overlapping weeds with maize seedlings， and similar morphology.Its compact size and computational efficiency make it suitable for the deployment in mobile devices for controlling weeds during the stage of seedling.

关键词

Keywords

references

张帅，高国文，吴莉莉，等.增效剂及微肥与种衣剂协同施用评价玉米茎腐病的防效［J］.新疆农业科学，2024，61（S1）：19-27. ZHANG S，GAO G W，WU L L，et al.Evaluation of the synergistic application of seed coating agents，synergists，and micro fertilizers for the prevention and control of corn stem rot disease［J］.Xinjiang agricultural sciences，2024，61（S1）：19-27 （in Chinese） .

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，2021，21（1）：212［2025-10-05］.https：//doi.org/10.3390/s21010212.

刘冰杰，周雅楠，周小辉，等.基于深度学习的玉米田间杂草识别模型研究［J］.河南农业大学学报，2024，58（2）：279-286. LIU B J，ZHOU Y N，ZHOU X H，et al.Deep learning-based weed recognition model in the maize field［J］.Journal of Henan Agricultural University，2024，58（2）：279-286 （in Chinese with English abstract） .

冀汶莉，刘洲，邢海花.基于YOLOv5的农田杂草识别轻量化方法研究［J］.农业机械学报，2024，55（1）：212-222.JI W L，LIU Z，XING H H.Lightweight method for identifying farmland weeds based on YOLO v5［J］.Transactions of the CSAM，2024，55（1）：212-222 （in Chinese with English abstract） .

崔钰.基于改进YOLOv5s田间大豆玉米幼苗及伴生杂草检测算法的研究［D］.太谷：山西农业大学，2024. CUI Y.Research on detection algorithm of soybean and corn seedlings and associated wee ds in field based on improved YOLOv5s［D］.Taigu：Shanxi Agricultural University，2024 （in Chinese with English abstract） .

范晓霞.基于改进YOLOv7的玉米幼苗和杂草识别模型研究［D］.大庆：黑龙江八一农垦大学，2025. FAN X X.Research on corn seedling and weed recognition model based on improved YOLOv7［D］.Daqing：Heilongjiang Bayi Agricultural University，2025 （in Chinese with English abstract） .

张天宇，韩静，廖洪晖，等.基于优化YOLOv5算法的玉米苗间杂草检测研究［J］.中国农机化学报，2025，46（7）：220-225. ZHANG T Y，HAN J，LIAO H H，et al.Research on weed detection among maize seedlings based on optimized YOLOv5 algorithm［J］.Journal of Chinese agricultural mechanization，2025，46（7）：220-225 （in Chinese with English abstract） .

陈雪，谭峰.基于改进YOLOv5的轻量级大豆田间杂草识别方法研究［J］.农机使用与维修，2025（2）：1-7. CHEN X，TAN F.Research on lightweight soybean field weed identification method based on improved YOLOv5［J］.Farm machinery using & maintenance，2025（2）：1-7 （in Chinese with English abstract） .

崔岩，庄卫东，秦韬，等.基于改进YOLOv5的玉米植株检测与识别研究［J］.中国农机化学报，2025，46（6）：136-141. CUI Y，ZHUANG W D，QIN T，et al.Detection and identification of maize plants based on improved YOLOv5［J］.Journal of Chinese agricultural mechanization，2025，46（6）：136-141 （in Chinese with English abstract） .

史丽晨，杨超，刘雪超，等.基于CDD-YOLO的轻量级低光照目标检测算法［J］.计算机工程与应用，2025，61（6）：106-117. SHI L C，YANG C，LIU X C，et al.Lightweight low-light object detection algorithm based on CDD-YOLO［J］.Computer engineering an d applications，2025，61（6）：106-117 （in Chinese with English abstract） .

杜希望，李霞，唐腾飞，等.基于改进YOLOv8n的双模态杂草检测方法［J/OL］.天津理工大学学报，2024 （2024-10-30）［2025-10-05］.https：//link.cnki.net/urlid/12.1374.DU X W，LI X，TANG T F，et al.Bimodal weed detection method based on improved YOLOv8n［J/OL］.Journal of Tianjin University of Technology，2024 （2024-10-30）［2025-10-05］.https：//link.cnki.net/urlid/12.1374. （in Chinese with English abstract） .

ZHONG J C，CHEN J Y，MIAN A.DualConv：dual convolutional kernels for lightweight deep neural networks［J］.IEEE transactions on neural networks and learning systems，2023，34（11）：9528-9535.

刘娜，陈阳，葛嵩，等.基于通道优先卷积注意力和DualConv的多人姿态估计［J/OL］.天津理工大学学报，2024 （2024-11-22）［2025-10-05］.https：//link.cnki.net/urlid/12.1374.N.20241122.1417.051.LIU N，CHEN Y，GE S，et al.Multiple person pose estimation based on channel prior convolutional attention and DualConv［J/OL］.Journal of Tianjin University Of Technology，2024 （2024-11-22）［2025-10-05］.https：//link.cnki.net/urlid/12.1374.N.20241122.1417.051 （in Chinese with English abstract） .

孙杰.基于改进YOLOv8的工厂火灾烟雾检测方法研究［J］.信息技术与信息化，2024（12）：100-103.SUN J.Research on smoke detection method of factory fire based on improved YOLOv8［J］.Information technology and informatization，2024（12）：100-103 （in Chinese） .

王铭振，赵扬，黄玉峰，等.基于YOLOv10的钛合金表面缺陷检测轻量化算法研究［J］.激光技术， 2026， 50 （1）：138-146.WANG M Z，ZHAO Y，HUANG Y F，et al.Lightweight algorithm for titanium alloy surface defect detection based on YOLOv10 ［J］.Laser technology，2026，50（1）：138-146 （in Chinese with English abstract） .

GAO Z G，YU X Y，RONG X W，et al.Improved YOLOv8n for lightweight ship detection［J/OL］.Journal of marine science and engineering，2024，12（10）：1774［2025-10-05］.https：//doi.org/10.3390/jmse12101774.

SUNKARA R，LUO T.No more strided convolutions or pooling：a new CNN building block for low-resolution images and small objects［M］//Machine learning and knowledge discovery in databases.Cham：Springer Nature Switzerland，2023：443-459.

刘愚成，梁新成，李法霖，等.基于改进YOLOv8的柠檬果实识别方法［J］.西南大学学报（自然科学版），2025，47（7）：219-230.LIU Y C，LIANG X C，LI F L，et al.A lemon fruit recognition method based on improved YOLOv8［J］.Journal of Southwest University （natural science edition），2025，47（7）：219-230 （in Chinese with English abstract） .

LU Y，SUN M H.Lightweight multidimensional feature enhancement algorithm LPS-YOLO for UAV remote sensing target detection［J/OL］.Scientific reports，2025，15：1340［2025-10-05］.https：//doi.org/10.1038/s41598-025-85488-z.

WANG H J，FU X Y，YU Z X，et al.DSS-YOLO：an improved lightweight real-time fire detection model based on YOLOv8［J/OL］.Scientific reports，2025，15：8963［2025-10-05］.https：//doi.org/10.1038/s41598-025-93278-w.

MIAO Y Z，MENG W，ZHOU X Y.SerpensGate-YOLOv8：an enhanced YOLOv8 model for accurate plant disease detection［J/OL］.Frontiers in plant science，2025，15：1514832［2025-10-05］.https：//doi.org/10.3389/fpls.2024.1514832.

HE K M，ZHANG X Y，REN S Q，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition［J］.IEEE transactions on pattern analysis and machine intelligence，2015，37（9）：1904-1916．

ZHANG X D，ZENG H，GUO S，et al.Efficient long-range attention network forImage super-resolution［C］//Computer Vision-ECCV 2022.Cham：Springer，2022，649-667.

齐勇杰，马纪龙，韩林蒲，等.基于改进YOLOv8s的轻量化玉米苗期杂草识别模型［J］.西北农林科技大学学报（自然科学版），2025，53（11）：58-70. QI Y J，MA J L，HAN L P，et al.Lightweight maize seedling weed identification model based on improved YOLOv8s［J/OL］.Journal of Northwest A & F University （natural science edition），53（11）：58-70 （in Chinese with English abstract） .

ZHENG Z H，WANG P，REN D W，et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation［J］.IEEE transactions on cybernetics，2022，52（8）：8574-8586.

王会征，刘海藤，李新龙，等.基于改进YOLOv8n的轻量化草坪异质杂草检测算法［J］.农业工程学报，2025，41（10）：157-165.WANG H Z，LIU H T，LI X L，et al.Detecting lawn heterogeneous weed using lightweight improved YOLOv8n［J］.Transactions of the CSAE，2025，41（10）：157-165 （in Chinese with English abstract） .

LI Y，TENG S R，CHEN J J，et al.FEI-YOLO：a lightweight soybean pod-type detection model［J/OL］.Agronomy，2024，14（11）：2526［2025-10-05］.https：//doi.org/10.3390/agronomy14112526.

ZHANG H， XU C， ZHANG S.Inner-IoU： more effective intersection over union loss with auxiliary bounding box［PP/OL］.arXiv，2023：2311.02877［2025-10-05］.https：//doi.org/10.48550/arXiv.2311.02877.

HUANG P P，TIAN S H，SU Y，et al.IA-CIOU：an improved IOU bounding box loss function for SAR ship target detection methods［J］.IEEE journal of selected topics in applied earth observations and remote sensing，2024，17：10569-10582.

BING S，YUEYANG Z，YIFENG L，et al.Pest-YOLOv8：enhanced detection for small and complex agricultural pests using triple attention and wise-IoU［J/OL］.Journal of plant diseases and protection，2025，132：135［2025-10-05］.https：//doi.org/10.1007/s41348-025-01134-w.

王鑫怡，刘旭腾，郑纪业，等.基于改进YOLOv8的轻量级鱼类检测方法［J］.渔业现代化，2024，51（6）：91-99.WANG X Y，LIU X T，ZHENG J Y，et al.Lightweight fish detection method based on improved YOLOv8［J］.Fishery modernization，2024，51（6）：91-99 （in Chinese with English abstract） .

CAI S B，ZHANG X K，MO Y C.A lightweight underwater detector enhanced by attention mechanism，GSConv and WIoU on YOLOv8［J/OL］.Scientific reports，2024，14：25797［2025-10-05］.https：//doi.org/10.1038/s41598-024-75809-z.

GUO F，GUO X，GUO L，et al.Target detection of diamond nanostructures based on improved YOLOv8 modeling［J/OL］.Nanomaterials，2024，14（13）：1115［2025-10-05］.https：//doi.org/10.3390/nano14131115.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A pruning and knowledge distillation-based YOLOv8 lightweight method for detecting leaf diseases in apple

Effects of gypsum combined with organic materials on alkalized solonchaks and growth of maize

Mechanism of ZmDIR11 regulating resistance to salt stress in maize

Facial recognition of Angus cattle based on the improved YOLOv8n

Hydroponic planting of lettuce with pig-farm biogas slurry UF-NF-RO concentration

Related Author

ZHANG Shuaiping

SHI Lei

ZHENG Guang

WANG Huixin

YIN Fei

FAN Liqin

SHEN Jingli

WANG Xu

Related Institution

College of Information & Management Sciences， Henan Agricultural University

Institute of Agricultural Resources and Environment，Ningxia Academy of Agriculture and Forestry Sciences/Station of Observation and Experiment， National Agricultural Environment in Yinchuan

Institute of Crop Breeding and Cultivation， Shanghai Academy of Agricultural Sciences/ CIMMYT⁃China Special Maize Research Center/Shanghai Engineering Research Center of Specialty Maize/Shanghai Key Laboratory of Agricultural Genetics and Breeding

College of Fisheries and Life Sciences， Shanghai University of Ocean

Ministry of Agriculture and Rural Affairs Key Laboratory of Smart Farming for Agriculltural Animals/ College of Information，Huazhong Agricultural University

AI问答

⁰