| 335 | 0 | 600 |
| 下载次数 | 被引频次 | 阅读次数 |
针对复杂真实场景下甜菜田间杂草识别效率低、精确率低、小目标漏检等问题，提出一种基于YOLOv11模型改进的甜菜田间杂草识别算法。在主干网络引入PoolFormer模块和AKConv模块增强模型对全局语义信息的捕捉能力来提升检测精度，提高了在低分辨率图像和小物体中的检测效果。AKConv模块通过动态调整卷积核参数和形状，提升模型对生长形态不规则的甜菜与杂草的特征提取能力；PoolFormer模块可以很好地将相互遮盖的甜菜与杂草的边缘特征进行分割。在头部网络加入高级筛选-特征融合金字塔网络(High-level Screening Feature Pyramid Network, HS-FPN)模块增强多尺度融合效率，提升幼苗期甜菜与杂草的特征提取效率和速度。通过实验得出，改进YOLOv11模型的精确率、召回率、mAP@0.5、mAP@0.5:0.95相较于改进前分别提升了6.9%、7.8%、7.9%、7.8%。结果表明，在甜菜田间杂草识别上取得了显著的提升效果，为复杂场景中检测甜菜田间杂草提供了一个更可行的解决方案。
Abstract：An algorithm for weed recognition in beet fields based on improved YOLOv11 model is proposed to address the problems of low efficiency, low accuracy, and missed detection of small targets in complex real-world scenarios.The PoolFormer module and AKConv module are introduced into the backbone network to enhance the model's ability to capture global semantic information to improve detection accuracy, enhancing the detection performance in low resolution images and small objects.The AKConv module improves the feature extraction ability of the model for beets and weeds with irregular growth patterns by dynamically adjusting the convolution kernel parameters and shapes, while the PoolFormer module can effectively segment the edge features of beets and weeds that cover each other.Secondly, the High-level Screening Feature Pyramid Network(HS-FPN) module is added to the head network to enhance the efficiency of multi-scale fusion and improve the feature extraction efficiency and speed of beets and weeds during the seedling stage.Through experiments, it is found that the improved YOLOv11 model achieves increases of 6.9%,7.8%,7.9%,and 7.8% in precision, recall, mAP@0.5 and mAP@0.5:0.95,respectively, compared to the original model.The results show that this algorithm has achieved significant improvement in weed recognition in beet fields, providing a more feasible solution for detecting weeds in beet fields in complex scenarios.
[1] 沈涛，张秀再，许岱.改进RT-DETR的遥感图像小目标检测算法[J].计算机科学，2025,52(8):214-221.
[2] 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.
[3] 袁洪波，赵努东，程曼.基于图像处理的田间杂草识别研究进展与展望[J].农业机械学报，2020,51(增刊2):323-334.
[4] 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.
[5] 文韬，王天一，黄诗锐，等.基于改进YOLOv8的农作物与藜草检测算法：MES-YOLO[J/OL].计算机工程与科学，1-13[2025-06-15].https://link.cnki.net/urlid/43.1258.tp.20241011.1309.004.
[6] 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，1-10[2025-05-15].https://link.cnki.net/urlid/12.1374.N.20241029.1920.024.
[7] 冀汶莉，刘洲，邢海花.基于YOLO v5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.
[8] 彭明霞，夏俊芳，彭辉.融合FPN的Faster R-CNN复杂背景下棉田杂草高效识别方法[J].农业工程学报，2019,35(20):202-209.
[9] 杨明轩，陈琳.改进YOLOv5的棉田杂草检测[J].现代电子技术，2024,47(24):60-67.
[10] 罗柳茗，李岩舟，石美琦，等.基于YOLOv8n的甘蔗杂草识别方法[J].中国农机化学报，2025,46(2):237-244.
[11] 林宗缪，马超，胡冬.基于改进YOLOv8卷积神经网络的稻田苗期杂草检测方法[J].湖北农业科学，2024,63(8):17-22.
[12] DARBYSHIRE M,SALAZAR-GOMEZ A,GAO J F,et al.Towards Practical Object Detection for Weed Spraying in Precision Agriculture [J].Frontiers in Plant Science,2023,14:1183277.
[13] KHANAM R,HUSSAIN M.YOLOv11:An Overview of the Key Architectural Enhancements [EB/OL].(2024-10-23)[2025-05-10].https://arxiv.org/abs/2410.17725.
[14] ZHANG R T,ZHU D J,WU C,et al.Sensitive Information Detection Based on Deep Learning Models [J].Applied Sciences,2024,14(17):7541.
[15] HIDAYATULLAH P,SYAKRANI N,SHOLAHUDDIN M R,et al.YOLOv8 to YOLO11:A Comprehensive Architecture In-depth Comparative Review[EB/OL].(2025-01-23)[2025-05-11].https://arxiv.org/abs/2501.13400.
[16] 马艺嘉，卢睿智，付可欣，等.基于MBL-YOLOv8n模型的光伏缺陷检测[J].无线电工程，2025,55(8):1703-1709.
[17] 李璐，陈清江.基于超分辨率和YOLO的红外小目标检测 [J].无线电工程，2025,55(8):1571-1579.
[18] QIN J H,PAN W Y,XIANG X Y,et al.A Biological Image Classification Method Based on Improved CNN[J].Ecological Informatics,2020,58:11093.
[19] YANG E Q,ZHOU W J,QIAN X H,et al.DRNet:Dual-stage Refinement Network with Boundary Inference for RGB-D Semantic Segmentation of Indoor Scenes [J].Engineering Applications of Artificial Intelligence,2023,125:106729.
[20] WANG X,HE N,HONG C,et al.Improved YOLOX-X Based UAV Aerial Photography Object Detection Algorithm[J].Image and Vision Computing,2023,135:104697.
[21] ZHU X Z,HU H,LIN S,et al.Deformable ConvNets v2:More Deformable,Better Results[EB/OL].(2018-11-27)[2025-05-11].https://arxiv.org/abs/1811.11168.
[22] ZHANG X,SONG Y Z,SONG T T,et al.AKConv:Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters[EB/OL].(2023-11-20)[2025-05-11].https://arxiv.org/abs/2311.11587v1.
[23] JIA Z Y,ZHANG M,YUAN C,et al.ADL-YOLOv8:A Field Crop Weed Detection Model Based on Improved YOLOv8[J].Agronomy,2024,14(10):2355.
[24] SUN H,TAN C H,PANG S,et al.RA-YOLOv8:An Improved YOLOv8 Seal Text Detection Method [J].Electronics,2024,13(15):3001.
[25] CHEN Y F,ZHANG C Y,CHEN B,et al.Accurate Leukocyte Detection Based on Deformable-DETR and Multi-level Feature Fusion for Aiding Diagnosis of Blood Diseases[EB/OL].(2024-01-01)[2025-05-11].https://arxiv.org/abs/2401.00926.
[26] LIU R M,SU W H.APHS-YOLO:A Lightweight Model for Real-time Detection and Classification of Stropharia Rugoso-Annulata [J].Foods,2024,13(11):1710.
[27] XIN D Y,LI T Q.Revolutionizing Tomato Disease Detection in Complex Environments[J].Frontiers in Plant Science,2024,15:1409544.
[28] MA X W,YANG J W,HONG T F,et al.STNet:Spatial and Temporal Feature Fusion Network For Change Detection in Remote Sensing Images[C]//2023 IEEE International Conference on Multimedia and Expo (ICME).Brisbane:IEEE,2023:2195-2200.
[29] VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[EB/OL].(2017-06-12)[2025-05-12].https://arxiv.org/abs/1706.03762.
[30] YU W H,LUO M,ZHOU P,et al.MetaFormer Is Actually What You Need for Vision [EB/OL].(2021-11-12)[2025-05-10].https://arxiv.org/abs/2111.11418.
[31] LIAO Y N,HUANG C Y,ZHANG T,et al.China 05 Bone Age Assessment Based on Deep Learning[J].The Journal of China Universities of Posts and Telecommunications,2024,31(6):66-75.
基本信息:
中图分类号:S451;S566.3;TP183;TP391.41
引用信息:
[1]周子健,刘强.基于改进的YOLOv11甜菜田间杂草识别算法研究[J].无线电工程,2025,55(11):2184-2194.
基金信息:
国家自然科学基金(32360438)~~
2025-11-05
2025-11-05