基于深度学习的草坪杂草识别与除草剂喷施区域检测方法

doi:10.11733/j.issn.1007-0435.2022.06.027

草地学报 ›› 2022, Vol. 30 ›› Issue (6): 1543-1549.DOI: 10.11733/j.issn.1007-0435.2022.06.027

• 研究论文 • 上一篇

基于深度学习的草坪杂草识别与除草剂喷施区域检测方法

金小俊¹, 孙艳霞², 陈勇¹, 于佳琳³

1. 南京林业大学机械电子工程学院, 江苏南京 210037;
2. 南京交通职业技术学院轨道交通学院, 江苏南京 211188;
3. 得克萨斯农工大学土壤与作物科学系, 得克萨斯州学院站 77843

收稿日期:2021-11-08 修回日期:2021-12-01 发布日期:2022-07-05
通讯作者: 陈勇,E-mail:chenyongjsnj@163.com;于佳琳,E-mail:yu.jialin@tamu.edu
作者简介:金小俊(1987-),男,汉族,江苏姜堰人,博士研究生、工程师,主要从事计算机视觉与人工智能技术研究,Email:xiaojun.jin@outlook.com
基金资助:
国家自然科学基金项目（32072498）；江苏省重点研发计划项目（BE2021016）；江苏省农业科技自主创新资金项目（CX（21）3184）资助

Weed Recognition and Herbicide Spraying Area Detection in Turf Based on Deep Learning

JIN Xiao-jun¹, SUN Yan-xia², CHEN Yong¹, YU Jia-lin³

1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, Jiangsu Province 210037, China;
2. School of Rail Transportation, Nanjing Vocational Institute of Transport Technology, Nanjing, Jiangsu Province 211188, China;
3. Department of Soil and Crop Sciences, Texas A&M University, College Station, Texas 77843, USA

Received:2021-11-08 Revised:2021-12-01 Published:2022-07-05

摘要/Abstract

摘要： 本文以狗牙根草坪及其伴生杂草毛花雀稗、白三叶以及莎草为研究对象，提出了一种基于深度学习的草坪杂草识别及除草剂喷施区域检测方法。通过将原图划分为若干格子区域，利用神经网络模型对格子图片进行杂草识别，实现杂草定位并进而确定除草剂喷施区域。为探究不同神经网络模型对杂草识别的效果，选取VGGNet模型、GoogLeNet模型和ShuffleNet模型，分别以F₁值、准确率和识别速度进行对比分析。验证集下所有模型的F₁值都高于0.97，表明本研究中的三个模型对于杂草都有较好的识别效果。其中，GoogLeNet模型为杂草识别最优模型，拥有最为均衡的识别率和识别速度。其在测试集的平均准确率和识别速度分别为98.75%和36.9 fps，能够用于草坪实时杂草识别应用。结果表明，本研究提出的草坪杂草识别与除草剂喷施区域检测方法具有高度的可行性和较优的应用效果，可用于基于除草剂精准喷施的草坪杂草防控。

关键词: 草坪杂草, 杂草识别, 深度学习, 喷施区域, 图像处理

Abstract: This paper proposed a method of turf weed recognition and accurate spraying based on deep learning. The research targets of this paper are bermudagrass lawn and its associated weeds,including dallisgrass,white clover,and purple nutsedge. By dividing the original image into several grid regions,the convolutional neural network model was used to identify the grid subimages,locate weed position,and determine the precise spraying area of herbicides. In order to explore the effects of different deep learning models on weed recognition,the VGGNet model,the GoogLeNet model,and the ShuffleNet model were selected to compare and analyze in terms of F₁ value,accuracy,and recognition speed. The F₁ value of all models under the verification set was higher than 0.97,indicating that the three models in this study have a good recognition effect on weeds. The GoogLeNet model was the most optimal weed recognition model,with the most balanced recognition rate and recognition speed. Its average accuracy and identification speed in the test set were 98.75% and 36.9 fps,respectively,which can be used in real-time weed recognition applications on turf. The results showed that the turf weed identification and herbicide precision spraying areas detection has highly feasible and excellent application effect,and can be used for turfgrass weed control based on precise herbicide spraying.

Key words: Turf weed, Weed recognition, Deep learning, Site-specific spraying, Image processing

中图分类号:

TP391.41

金小俊, 孙艳霞, 陈勇, 于佳琳. 基于深度学习的草坪杂草识别与除草剂喷施区域检测方法[J]. 草地学报, 2022, 30(6): 1543-1549.

JIN Xiao-jun, SUN Yan-xia, CHEN Yong, YU Jia-lin. Weed Recognition and Herbicide Spraying Area Detection in Turf Based on Deep Learning[J]. Acta Agrestia Sinica, 2022, 30(6): 1543-1549.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://manu40.magtech.com.cn/Jweb_cdxb/CN/10.11733/j.issn.1007-0435.2022.06.027

https://manu40.magtech.com.cn/Jweb_cdxb/CN/Y2022/V30/I6/1543

参考文献

[1] 李永武,葛应兰. 草坪杂草的主要种类,发生特点与综合防除[J]. 河南农业,2014(10):47-48
[2] 赵娜,徐庆国,苏鹏,等. 7个暖季型草坪草品种对低温胁迫的抗性差异研究[J]. 草地学报,2020,28(2):375-382
[3] 赵艳岭,刘志强,邢红华,等. 绿地草坪的管理与养护[J]. 河南科技:上半月,2007(9):65-66
[4] 曹晓会. 草坪杂草的危害及其防治[J]. 现代园艺,2017(11):137-138
[5] 泰尔格力,蔡金宏,崔凤超,等. 野牛草草坪除草剂安全施用策略[J]. 草地学报,2021,29(9):1865-1876
[6] 束放,熊延坤,韩梅. 2015年我国农药生产与使用概况[J]. 农药科学与管理,2016(7):1-6
[7] 吴向辉. 农业部首次公布化肥,农药利用率数据[J]. 江西农业,2015(12):48
[8] 郭利京,王颖. 我国水稻生产中农药过量施用研究:基于社会和私人利益最大化的视角[J]. 生态与农村环境学报,2018,34(5):401-407
[9] 陈海涛,丁伟,许安定,等. 烟田农药减量增效施药技术的关键因素分析[J]. 江苏农业科学,2012(11):125-127
[10] 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
[11] DAI X,XU Y,ZHENG J,et al. Analysis of the variability of pesticide concentration downstream of inline mixers for direct nozzle injection systems[J]. Biosystems Engineering,2019(180):59-69
[12] 金小俊,陈勇,孙艳霞. 农田杂草识别方法研究进展[J]. 农机化研究,2011,33(07):23-7,33
[13] HAMUDA E,GLAVIN M,JONES E. A survey of image processing techniques for plant extraction and segmentation in the field[J]. Computers and Electronics in Agriculture,2016(125):184-199
[14] 韩万强,靳瑰丽,岳永寰,等. 基于高光谱成像技术的伊犁绢蒿荒漠草地主要植物识别参数的筛选[J]. 草地学报,2020,28(4):1153-1163
[15] 仇裕淇,黄振楠,阮昭,等. 机器视觉技术在农业生产智能化中的应用综述[J]. 机械研究与应用,2019,32(02):202-206
[16] WANG A,ZHANG W,WEI X. A review on weed detection using ground-based machine vision and image processing techniques[J]. Computers and Electronics in Agriculture,2019(158):226-240
[17] JORDAN M I,MITCHELL T M. Machine learning:Trends,perspectives,and prospects[J]. Science,2015,349(6245):255-260
[18] GU J,WANG Z,KUEN J,et al. Recent advances in convolutional neural networks[J]. Pattern Recognition,2018(77):354-377
[19] SCHMIDHUBER J. Deep learning in neural networks:An overview[J]. Neural Networks,2015(61):85-117
[20] SHI J,LI Z,ZHU T,et al. Defect detection of industry wood veneer based on NAS and multi-channel mask R-CNN[J]. Sensors,2020,20(16):4398
[21] YU Y,LIU Y,CHEN J,et al. Detection Method for Bolted Connection Looseness at Small Angles of Timber Structures based on Deep Learning[J]. Sensors,2021,21(9):3106
[22] 王璨,武新慧,张燕青,等. 基于双注意力语义分割网络的田间苗期玉米识别与分割[J]. 农业工程学报,2021,37(9):211-221
[23] 樊湘鹏,周建平,许燕,等. 基于优化Faster R-CNN的棉花苗期杂草识别与定位[J]. 农业机械学报,2021,52(5):26-34
[24] OSORIO K,PUERTO A,PEDRAZA C,et al. A Deep Learning Approach for Weed Detection in Lettuce Crops Using Multispectral Images[J]. AgriEngineering,2020,2(3):471-488
[25] YU J,SCHUMANN A W,CAO Z,et al. Weed Detection in Perennial Ryegrass With Deep Learning Convolutional Neural Network[J]. Frontiers in plant science,2019(10):1422
[26] YU J,SCHUMANN A W,SHARPE S M,et al. Detection of grassy weeds in bermudagrass with deep convolutional neural networks[J]. Weed Science,2020,68(5):545-552
[27] YU J,SHARPE S M,SCHUMANN A W,et al. Deep learning for image-based weed detection in turfgrass[J]. European Journal of Agronomy,2019(104):78-84
[28] YU J,SHARPE S M,SCHUMANN A W,et al. Detection of broadleaf weeds growing in turfgrass with convolutional neural networks[J]. Pest management science,2019,75(8):2211-2218
[29] 李春明,逯杉婷,远松灵,等. 基于Faster R-CNN的除草机器人杂草识别算法[J]. 中国农机化学报,2019,40(12):171-176
[30] PASZKE A,GROSS S,MASSA F,et al. Pytorch:An imperative style,high-performance deep learning library[J]. Advances in neural information processing systems,2019(32):8026-8037
[31] 舒娜,刘波,林伟伟,等. 分布式机器学习平台与算法综述[J]. 计算机科学,2019,46(3):9-18
[32] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:14091556,2014
[33] SZEGEDY C,LIU W,JIA Y,et al. Going deeper with convolutions[C]//proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition,2015,San Juan,PR,USA
[34] ZHANG X,ZHOU X,LIN M,et al. Shufflenet:An extremely efficient convolutional neural network for mobile devices[C]//proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition,San Juan,PR,USA,2018
[35] 马志艳,朱熠,杨磊. 基于视觉的苗期作物株间除草关键技术研究现状[J]. 中国农机化学报,2020,41(02):32-38
[36] BARBEDO J G A,KOENIGKAN L V,SANTOS T T,et al. A study on the detection of cattle in UAV images using deep learning[J]. Sensors,2019,19(24):5436
[37] BIANCO S,CADENE R,CELONA L,et al. Benchmark analysis of representative deep neural network architectures[J]. IEEE Access,2018(6):64270
[38] LEE R B. Realtime MPEG video via software decompression on a PA-RISC processor[C]//proceedings of the Digest of Papers COMPCON'95 Technologies for the Information Superhighway,San Jose,California,USA,1995

基于深度学习的草坪杂草识别与除草剂喷施区域检测方法

Weed Recognition and Herbicide Spraying Area Detection in Turf Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	陈海燕, 曹明华, 王惠琴, 胡家琪. 一种基于图像处理技术的高原鼠兔识别方案[J]. , 2011, 19(3): 516-519.
[2]	王敬轩, 冯全, 王宇通, 邵新庆. 基于图像识别技术的豆科牧草分类研究[J]. , 2010, 18(1): 37-41.
[3]	朱晶晶, 强胜. 气象因子对南京市草坪夏秋季杂草发生的影响[J]. , 2005, 13(2): 97-101.