|
|
|
| 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 |
|
|
|
|
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.
|
|
Received: 15 April 2018
|
|
|
|
| [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. 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)[2]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.[3]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)[4]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.[5]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.[6]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.[7]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.[8]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.[9]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. |
|
|
|
