|本期目录/Table of Contents|

[1]黄友锐,王小桥,韩涛,等.基于改进YOLO v8n的甜菜杂草检测算法研究[J].江苏农业科学,2024,52(24):196-204.
 Huang Yourui,et al.A detection method for sugar beets and weeds based on improved YOLO v8n algorithm[J].Jiangsu Agricultural Sciences,2024,52(24):196-204.
点击复制

基于改进YOLO v8n的甜菜杂草检测算法研究(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24期
页码:
196-204
栏目:
农业工程与信息技术
出版日期:
2024-12-20

文章信息/Info

Title:
A detection method for sugar beets and weeds based on improved YOLO v8n algorithm
作者:
黄友锐12王小桥1韩涛1宋红萍1王照锋1
1.安徽理工大学电气与信息工程学院,安徽淮南 232001; 2.皖西学院电气与光电工程学院,安徽六安 237012
Author(s):
Huang Youruiet al
关键词:
甜菜杂草识别YOLO v8n感受野坐标注意力卷积小目标检测
Keywords:
-
分类号:
S126;TP319.41
DOI:
-
文献标志码:
A
摘要:
农作物生长过程中其伴生杂草的及时清除能够有效提高农作物的产量和质量。针对当前对于甜菜杂草检测精度较低、小目标漏检等问题,提出了基于改进YOLO v8n的甜菜杂草检测算法。首先,在检测头部分增加一个小目标检测层,提高模型对生长初期甜菜和杂草的检测能力。其次,在主干部分引入感受野坐标注意力卷积(receptive-field coordinated attention convolutional operation,RFCAConv),更好地识别图像中的边缘、纹理、形状等低级特征,并且所增加的计算开销极小。最后,引入损失函数PIoU v2替换YOLO v8n原来的损失函数,增强对中等质量锚框的聚焦能力,加快收敛速度,并提高检测精度。通过公开的Lincolnbeet数据集进行试验,试验结果表明,改进后的YOLO v8n模型总的mAP@0.5达到了0.902,对比YOLO v8n原模型提高了0.035,甜菜和杂草分别提升了0.026、0.041,参数量减少了3.3%,平均每幅图片的检测时间为4.1 ms,能够满足实时检测的要求。
Abstract:
-

参考文献/References:

[1]周艳丽,李晓威,刘娜,等. 内蒙古甜菜制糖产业发展探析[J]. 中国糖料,2020,42(2):59-64.
[2]刘晓雪,蒙威宇,谢由之. 甜菜生产大幅波动的原因探究:基于199份农户调查问卷[J]. 中国糖料,2024,46(2):92-102.
[3]汤雷雷,万开元,陈防. 养分管理与农田杂草生物多样性和遗传进化的关系研究进展[J]. 生态环境学报,2010,19(7):1744-1749.
[4]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(2):323-334.
[5]李彧,余心杰,郭俊先. 基于全卷积神经网络方法的玉米田间杂草识别[J]. 江苏农业科学,2022,50(6):93-100.
[6]孟庆宽,张漫,杨晓霞,等. 基于轻量卷积结合特征信息融合的玉米幼苗与杂草识别[J]. 农业机械学报,2020,51(12):238-245,303.
[7]毛文华,张银桥,王辉,等. 杂草信息实时获取技术与设备研究进展[J]. 农业机械学报,2013,44(1):190-195.
[8]姜红花,张传银,张昭,等. 基于Mask R-CNN的玉米田间杂草检测方法[J]. 农业机械学报,2020,51(6):220-228,247.
[9]苗中华,余孝有,徐美红,等. 基于图像处理多算法融合的杂草检测方法及试验[J]. 智慧农业,2020,2(4):103-115.
[10]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.
[11]翁杨,曾睿,吴陈铭,等. 基于深度学习的农业植物表型研究综述[J]. 中国科学(生命科学),2019,49(6):698-716.
[12]Li Y,Guo Z Q,Shuang F,et al. Key technologies of machine vision for weeding robots:a review and benchmark[J]. Computers and Electronics in Agriculture,2022,196:106880.
[13]胡盈盈,王瑞燕,郭鹏涛,等. 基于近地光谱特征的玉米田间杂草识别研究[J]. 江苏农业科学,2020,48(8):242-246.
[14]化春键,张爱榕,陈莹. 基于改进的Retinex算法的草坪杂草识别[J]. 江苏农业学报,2021,37(6):1417-1424.
[15]李柯泉,陈燕,刘佳晨,等. 基于深度学习的目标检测算法综述[J]. 计算机工程,2022,48(7):1-12.
[16]Ren S Q,He K M,Girshick R,et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
[17]He K M,Gkioxari G,Dollár P,et al. Mask R-CNN [C]//Proceedings of the IEEE International Conference on Computer Vision. Italy:IEEE Press,2017:2961-2969.
[18]Liu W,Anguelov D,Erhan D,et al. SSD:single shot MultiBox detector[C]//Computer Vision-ECCV 2016. Cham:Springer International Publishing,2016:21-37.
[19]Kumar P,Misra U. Deep learning for weed detection:exploring YOLO v8 algorithms performance in agricultural environments[C]//Proceedings of the 2024 2nd International Conference on Disruptive Technologies (ICDT). Greater Noida:IEEE Press,2024:255-258.
[20]Gallo I,Rehman A U,Dehkordi R H,et al. Deep object detection of crop weeds:performance of YOLO v7 on a real case dataset from UAV images[J]. Remote Sensing,2023,15(2):539.
[21]Ying B Y,Xu Y C,Zhang S,et al. Weed detection in images of carrot fields based on improved YOLO v4[J]. Traitement Du Signal,2021,38(2):341-348.
[22]Wang Q F,Cheng M,Huang S,et al. A deep learning approach incorporating YOLO v5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings[J]. Computers and Electronics in Agriculture,2022,199:107194.
[23]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.
[24]邓天民,程鑫鑫,刘金凤,等. 基于特征复用机制的航拍图像小目标检测算法[J]. 浙江大学学报(工学版),2024,58(3):437-448.
[25]Zheng Z H,Wang P,Liu W,et al. Distance-IoU loss:Faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12993-13000.
[26]Hou Q B,Zhou D Q,Feng J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville:IEEE Press,2021:13713-13722.
[27]Zhang X,Liu C,Yang D,et al. RFAConv:innovating spatial attention and standard convolutional operation [EB/OL]. arxiv preprint,arxiv:2304.03198v6(2023-04-06) [2024-04-07]. https://doi.org/10.48550/arXiv.2304.03198.
[28]Liu C,Wang K G,Li Q,et al. Powerful-IoU:more straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism[J]. Neural Networks,2024,170:276-284.
[29]Salazar-Gomez A,Darbyshire M,Gao J,et al. Beyond mAP:towards practical object detection for weed spraying in precision agriculture [C]//Proceedings of the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems. Kyoto Japan:IEEE Press,2022:9232-9238.

相似文献/References:

[1]王激清,刘社平,白晓瑛.盐胁迫对不同品种甜菜种子萌发特性的影响[J].江苏农业科学,2015,43(03):96.
 Wang Jiqing,et al.Effect of salt stress on germination characteristics of different varieties of sugar beet seeds[J].Jiangsu Agricultural Sciences,2015,43(24):96.
[2]费聪,王维成,李阳阳,等.氮素运筹对滴灌甜菜叶片光合特性的影响[J].江苏农业科学,2016,44(12):227.
 Fei Cong,et al.Effects of nitrogen management on photosynthetic characteristics of drip irrigated sugar beet[J].Jiangsu Agricultural Sciences,2016,44(24):227.
[3]高金秋,周建朝,王孝纯,等.部分高抗低磷胁迫基因型甜菜AFLP指纹图谱的构建[J].江苏农业科学,2017,45(06):36.
 Gao Jinqiu,et al.Establishment of AFLP fingerprint for some highly resistance and low-phosphorous sugar beet varieties[J].Jiangsu Agricultural Sciences,2017,45(24):36.
[4]杨荣超,田海清,李斐,等.基于甜菜冠层高光谱红边参数的SPAD值诊断[J].江苏农业科学,2017,45(11):153.
 Yang Rongchao,et al.SPAD value diagnosis based on red edge parameters of sugarbeet canopy hyperspectral[J].Jiangsu Agricultural Sciences,2017,45(24):153.
[5]张自强,白晨,张惠忠,等.甜菜雄性不育系高效组培再生体系的建立[J].江苏农业科学,2017,45(20):107.
 Zhang Ziqiang,et al.Establishment of high efficient tissue culture regeneration system of beet male sterile line[J].Jiangsu Agricultural Sciences,2017,45(24):107.
[6]张晶,张珏,王辉,等.甜菜光谱与生长信息相关性分析[J].江苏农业科学,2018,46(03):132.
 Zhang Jing,et al.Correlation analysis of spectrum and growth information of sugar beet[J].Jiangsu Agricultural Sciences,2018,46(24):132.
[7]费聪,王维成,李阳阳,等.利用Greenseeker法诊断甜菜氮素营养状况[J].江苏农业科学,2018,46(04):128.
 Fei Cong,et al.Nitrogen nutrition analysis of sugar beet by Greenseeker[J].Jiangsu Agricultural Sciences,2018,46(24):128.
[8]梁文洁,张丽,郭新勇,等.MLL启动子驱动SST基因转化甜菜的抗旱性分析[J].江苏农业科学,2018,46(05):43.
 Liang Wenjie,et al.Drought resistance of transformed sugar beet with SST gene driven by promoter MLL[J].Jiangsu Agricultural Sciences,2018,46(24):43.
[9]李国龙,孙亚卿,邵世勤,等.甜菜幼苗叶片渗透调节系统及部分激素对干旱胁迫的响应[J].江苏农业科学,2018,46(07):80.
 Li Guolong,et al.Response of osmoregulation system and some hormones to drought stress in sugar beet leaves during seedling stage[J].Jiangsu Agricultural Sciences,2018,46(24):80.
[10]胡盈盈,王瑞燕,郭鹏涛,等.基于近地光谱特征的玉米田间杂草识别研究[J].江苏农业科学,2020,48(8):242.
 Hu Yingying,et al.Recognition of weeds in maize fields based on near-earth spectrum characteristics[J].Jiangsu Agricultural Sciences,2020,48(24):242.

备注/Memo

备注/Memo:
收稿日期:2024-07-08
基金项目:安徽省高校协同创新项目(编号:GXXT-2023-068)。
作者简介:黄友锐(1971—),男,安徽淮南人,博士,教授,主要从事智能控制、智能制造研究。E-mail:hyr628@163.com。
通信作者:王小桥,硕士研究生,主要从事图像处理研究。E-mail:2022200878@aust.edu.cn。
更新日期/Last Update: 2024-12-20