排灌机械工程学报
   首页  学报介绍  编 委 会  作者园地  征订启事  编校法规  编读往来  录用公告  广告合作   行业新闻  留  言  English 
排灌机械工程学报  2018, Vol. 36 Issue (11): 1137-1141    DOI: 10.3969/j.issn.1674-8530.18.1131
泵理论与技术 最新目录 | 下期目录 | 过刊浏览 | 高级检索 Previous Articles  |  Next Articles  
基于深度学习的无人机遥感生态灌区杂草分类
王术波1, 韩宇2, 陈建1*, 潘越1, 曹毅1, 孟灏1
1.中国农业大学工学院, 北京 100083; 2.中国农业大学水利与土木工程学院, 北京 100083
Classification of weeds in ecological irrigation areas based on deep learning and remote sensing images taken by drone at low-altitude
WANG Shubo 1, HAN Yu 2, CHEN Jian1*, PAN Yue 1, CAO Yi1, MENG Hao1
1.College of Engineering, China Agricultural University, Beijing 100083, China; 2.College of Water Resource & Civil Engineering, China Agricultural University, Beijing 100083, China
 全文: PDF (1643 KB)   HTML (1 KB)   输出: BibTeX | EndNote (RIS)      背景资料
摘要 为了更好地推进生态灌区建设,对灌区内杂草进行检测、控制,提出一种基于卷积神经网络的杂草分类和密度测算方法.通过无人机低空拍摄采集3种杂草(藜草、葎草、苍耳)和3种作物(小麦、花生、玉米)作为数据集,经过裁剪、灰度化等前期处理,并通过旋转方式扩充数据集,最后收集17 115张训练样本和750张测试样本,然后将训练集输送给卷积神经网络,采用softmax回归,实现6类植物的分类.为降低网络参数,文中试验了100×100和300×300不同分辨率图像对识别精度的影响,分类结果表明300×300分辨率时识别率最高可达到95.6%.另外为实现针对特定杂草的防控,提出了一种检测单一杂草密度的方法,可实现对灌区内各种杂草的精确监控,为后期杂草防控的精准施药提供依据,对实现高效、绿色、安全的现代农业具有重要理论意义和实用价值.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
王术波
韩宇
陈建*
潘越
曹毅
孟灏
关键词生态灌区   无人机   卷积神经网络   杂草分类     
Abstract: In order to better promote the construction of ecological irrigation areas, it is required to detect and control weeds in the areas. Thus, in this paper a method was proposed based on convolutional neural network(CNN)for weed classification and density estimation in ecological irrigation areas.The images were taken by a drone at low-altitude for three kinds of weeds namely chenopodium album, humulusscandens and xanthium sibiricum as well as 3 sorts of crops such as wheat, peanut seeding and maize, and then 17 115 training samples and 750 test samples were harvested through trimming, gray scale and rotation. Finally, the training sets were input into the CNN, and the classification of 6 types of plants was conducted by means of softmax regression.In order to reduce the network parameters, the effect of 100×100 and 300×300 resolution images on recognition accuracy was also clarified.The results showed that the highest recognition rate of 300×300 resolution could reach as high as 95.6%accuracy.In order to prevent and control specific weeds, a method of detecting single weeds density was presented, too.Through this method, accurate monitoring of various weeds in irrigation areas can be achieved. This method can provide a basis for precise applying pesticide, and has important significance and theoretical and practical values for realizing efficient, green, and safe modern agriculture. 
Key wordsecological irrigation area   unmanned aerial vehicle(UAV)   convolutional neural network   weed classification   
收稿日期: 2018-04-15;
基金资助:

国家自然科学基金资助项目(51509248);国家重点研发计划项目(2017YFD0701000,2017YFC0403203,2016YFD200700,2016YFC0400207);中央高校基本科研业务费资助项目(2018QC128,2018SY007);吉林省重点科技研发项目(20180201036SF)

引用本文:   
王术波,韩宇,陈建*等. 基于深度学习的无人机遥感生态灌区杂草分类[J]. 排灌机械工程学报, 2018, 36(11): 1137-1141.
WANG Shu-Bo-,HAN Yu-,CHEN Jian-* et al. Classification of weeds in ecological irrigation areas based on deep learning and remote sensing images taken by drone at low-altitude[J]. Journal of Drainage and Irrigation Machinery Engin, 2018, 36(11): 1137-1141.
 
[1] 何军, 崔远来. 生态灌区农田排水沟塘湿地系统的构建和运行管理[J]. 中国农村水利水电, 2012(6):1-3.
[2] HE Jun, CUI Yuanlai. Farmland drainage ditch-pond wetland system′s construction and its operation management of ecological irrigation districts[J]. China rural water and hydropower, 2012(6):1-3.(in Chinese)
[3] ZHENG Y, ZHU Q, HUANG M, et al. Maize and weed classification using color indices with support vector data description in outdoor fields[J]. Computers & electro-nics in agriculture, 2017, 141:215-222.
[4] 刘伟, 赵庆展, 汪传建,等. 基于最小二乘支持向量机的无人机遥感影像分类[J]. 江苏农业科学, 2017, 45(9):187-191.
LIU Wei,ZHAO Qingzhan,WANG Chuanjian,et al. Classification of UAV remote sensing image based on least squares support vector machine [J].Jiangsu agricultural sciences,2017,45(9):187-191.(in Chinese)
[5] SA I, CHEN Z, POPOVIC M, et al. Weednet: dense semantic weed classification using multispectral images and Mav for smart farming[J]. IEEE robotics & automation letters, 2018, 3(1):588-595.
[6] AHMAD I, SIDDIQI M H, FATIMA I, et al. Weed classification based on Haar wavelet transform via k-nearest neighbor(k-NN)for real-time automatic sprayer control system[C]//Proceedings of the 5th international conference on ubiquitous information ma-nagement and communication,2011.
[7] VESALI F, GHARIBKHANI M, KOMARIZADEH M H. Performance evaluation of discriminant analysis and decision tree, for weed classification of potato fields[J]. Research journal of applied sciences engineering & technology, 2012, 4(18):3215-3221.
[8] LAVANIA S, MATEY P S. Novel method for weed classification in maize field using Otsu and PCA implementation[C]//2015 IEEE international conference on computational intelligence & communication technology. Ghaziabad, India:[s.n.],2015:534-537.
[9] ZHI S, LIU Y, LI X, et al. Towards real-time 3D object recognition: a lightweight volumetric CNN framework using multitask learning[J]. Computers & gra-phics, 2017,71:199-207.
[10] QAYYUM A, MALIK A S, SAAD N M, et al. Scene classification for aerial images based on CNN using sparse coding technique[J]. International journal of remote sensing, 2017, 38(8/9/10):2662-2685.
[1] 张自超, 韩宇, 陈建*, 王术波, 王广琦, 杜楠楠. 基于无人机遥感数据的生态渠系信息提取[J]. 排灌机械工程学报, 2018, 36(10): 1006-1011.
[2] 王大伟, 高席丰. 植保无人机药箱建模与姿态控制器设计[J]. 排灌机械工程学报, 2015, 33(11): 1006-1012.

江苏大学梦溪校区(镇江市梦溪园巷30号)图书馆5楼 0511-84440893 传真0511--84440033
Copyright 江苏大学杂志社 2010-2015 All Rights Reserved