Study on distribution map of weeds in rice field based on UAV remote sensing

ZHU Sheng; DENG Jizhong; ZHANG Yali; YANG Chang; YAN Zhiwei; XIE Yaoqing

doi:10.7671/j.issn.1001-411X.202006058

Journal of South China Agricultural University > 2020 > 41(6): 67-74. > DOI: 10.7671/j.issn.1001-411X.202006058

ZHU Sheng, DENG Jizhong, ZHANG Yali, et al. Study on distribution map of weeds in rice field based on UAV remote sensing[J]. Journal of South China Agricultural University, 2020, 41(6): 67-74. DOI: 10.7671/j.issn.1001-411X.202006058

Citation:

PDF (1337 KB)

Study on distribution map of weeds in rice field based on UAV remote sensing

National Center for International Collaboration Research on Precision Agricultural Aviation Pesticides Spraying Technology/College of Engineering, South China Agricultural University, Guangzhou 510642, China

More Information

Received Date: June 29, 2020
Available Online: May 17, 2023

Graphical Abstract

Abstract

Abstract

Objective
To obtain and analyze the low altitude remote sensing image of rice field, acquire the weed distribution map, and provide a reference for the precious pesticide application of weeds in the field.

Method
Three machine learning algorithms including support vector machine (SVM), K-nearest neighbor (KNN) and AdaBoost were used to classify and compare the weed visible light images in rice field captured by UAV after color feature extraction and principal component analysis (PCA) dimensionality reduction. A convolutional neural network (CNN) which can automatically obtain the image features without feature extraction and dimensionality reduction was introduced to classify the weed images and improve the classification accuracy.

Result
The run time of test set based on SVM, KNN and AdaBoost were 0.500 4, 2.209 2 and 0.411 1 s, and the classification accuracies were 89.75%, 85.58% and 90.25% respectively; The classification accuracy of image based on CNN was 92.41%, which was higher than those of three machine learning algorithms. All machine learning algorithms and CNN could effectively recognize rice and weed, acquire weed distribution information, and generate distribution map of weed in rice field.

Conclusion
The classification accuracy of weed in rice field based on CNN is the highest, and the weed distribution map generated by CNN is the best.
- UAV remote sensing,
- paddy weed,
- machine learning algorithm,
- convolutional neural network,
- precious pesticide application

FullText(HTML)

References (36)

References

[1]	姚中统. 新型助剂对玉米田除草剂增效作用及增效机制的研究[D]. 哈尔滨: 东北农业大学, 2019.
[2]	LOPEZ-GRANADOS F, TORRES-SANCHEZ J, SERRANO-PEREZ A, et al. Early season weed mapping in sunflower using UAV technology: Variability of herbicide treatment maps against weed thresholds[J]. Precis Agric, 2016, 17(2): 183-199. doi: 10.1007/s11119-015-9415-8
[3]	LAN Y, THOMSON S J, HUANG Y, et al. Current status and future directions of precision aerial application for site-specific crop management in the USA[J]. Comput Electron Agr, 2010, 74(1): 34-38. doi: 10.1016/j.compag.2010.07.001
[4]	LAN Y, CHEN S. Current status and trends of plant protection UAV and its spraying technology in China[J]. Int J Precis Agric Aviat, 2018, 1(1): 1-9. doi: 10.33440/j.ijpaa.20180101.0002
[5]	刘斌. 基于无人机遥感影像的农作物分类研究[D]. 北京: 中国农业科学院, 2019.
[6]	邓继忠, 任高生, 兰玉彬, 等. 基于可见光波段的无人机超低空遥感图像处理[J]. 华南农业大学学报, 2016, 37(6): 16-22.
[7]	PATHAK R, BARZIN R, BORA G C. Data-driven precision agricultural applications using field sensors and unmanned aerial vehicle (UAVs)[J]. Int J Precis Agric Aviat, 2018, 1(1): 19-23.
[8]	BARRERO O, ROJAS D, GONZALEZ C, et al. Weed detection in rice fields using aerial images and neural networks[C]//ALTUVE M. Symposium of image, signal processing, and artificial vision. New York: IEEE, 2016.
[9]	BARRERO O, PERDOMO S A. RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields[J]. Precis Agric, 2018, 19(5): 809-822. doi: 10.1007/s11119-017-9558-x
[10]	UTO K, SEKI H, SAITO G, et al. Characterization of rice paddies by a UAV-mounted miniature hyperspectral sensor system[J]. IEEE J-STARS, 2013, 6(2): 851-860.
[11]	马明洋. 基于无人机低空遥感的东北粳稻叶绿素含量估测方法研究[D]. 沈阳: 沈阳农业大学, 2018.
[12]	洪雪. 基于水稻高光谱遥感数据的植被指数产量模型研究[D]. 沈阳: 沈阳农业大学, 2017.
[13]	MA X, DENG X, QI L, et al. Fully convolutional network for rice seedling and weed image segmentation at the seedling stage in paddy fields[J]. PLoS One, 2019, 14(4): e0215676. doi: 10.1371/journal.pone.0215676
[14]	邓向武, 齐龙, 马旭, 等. 基于多特征融合和深度置信网络的稻田苗期杂草识别[J]. 农业工程学报, 2018, 34(14): 165-172.
[15]	陈晓红. 数据降维的广义相关分析研究[D]. 南京: 南京航空航天大学, 2011.
[16]	KARL PEARSON F R S. LIII: On lines and planes of closest fit to systems of points in space[J]. Philosophical Magazine Series 1, 1901, 11(2): 559-572.
[17]	HOTELLING H. Analysis of a complex of statistical variables into principal components[J]. J Educ Psychol, 1933, 24(6): 417-441. doi: 10.1037/h0071325
[18]	王小龙, 邓继忠, 黄华盛, 等. 基于高光谱数据的棉田虫害鉴别研究[J]. 华南农业大学学报, 2019, 40(3): 97-103.
[19]	曾伟辉. 面向农作物叶片病害鲁棒性识别的深度卷积神经网络研究[D]. 合肥: 中国科学技术大学, 2018.
[20]	SUN J, YANG J, ZHANG C, et al. Automatic remotely sensed image classification in a grid environment based on the maximum likelihood method[J]. Math Comput Model, 2013, 58(3/4): 573-581.
[21]	MILLER D M, KAMINSKY E J, RANA S. Neural network classification of remote-sensing data[J]. Comput Geosci, 1995, 21(3): 377-386. doi: 10.1016/0098-3004(94)00082-6
[22]	ZENG J, GUO H F, HU Y M. Artificial neural network model for identifying taxi gross emitter from remote sensing data of vehicle emission[J]. J Environ Sci, 2007, 19(4): 427-431. doi: 10.1016/S1001-0742(07)60071-0
[23]	BROWN M, LEWIS H G, GUNN S. Linear spectral mixture models and support vector machines for remote sensing[J]. IEEE T Geosci Remote, 2000, 38(5): 2346-2360. doi: 10.1109/36.868891
[24]	HUANG C, DAVIS L S, TOWNSHEND J R G. An assessment of support vector machines for land cover classification[J]. Int J Remote Sens, 2002, 23(4): 725-749. doi: 10.1080/01431160110040323
[25]	IRVIN B J, VENTURA S J, SLATER B K. Fuzzy and isodata classification of landform elements from digital terrain data in Pleasant Valley, Wisconsin[J]. Geoderma, 1997, 77(2/3/4): 137-154.
[26]	PAL S K, GHOSH A, SHANKAR B U. Segmentation of remotely sensed images with fuzzy thresholding, and quantitative evaluation[J]. Int J Remote Sens, 2000, 21(11): 2269-2300. doi: 10.1080/01431160050029567
[27]	王璨, 李志伟. 利用融合高度与单目图像特征的支持向量机模型识别杂草[J]. 农业工程学报, 2016, 32(15): 165-174.
[28]	唐美丽, 张劲松, 李璐, 等. 基于GPU的SVM参数优化并行算法[J]. 江苏大学学报(自然科学版), 2017, 38(5): 576-581.
[29]	CORTES C, VAPNIK V N. Support-vector networks[J]. 1995. doi: 10.1023/A: 1022627411411.
[30]	李春雨, 葛啸, 金燕婷, 等. 基于近红外光谱技术的蔬菜农药残留种类检测[J]. 农业工程, 2019, 9(6): 33-39.
[31]	黄欣, 莫海淼, 赵志刚. 基于自适应烟花算法和k近邻算法的特征选择算法[J]. 计算机应用与软件, 2020, 37(5): 268-274.
[32]	FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. J Comput Syst Sci, 1997, 55(1): 119-139. doi: 10.1006/jcss.1997.1504
[33]	杨国欣. 基于Adaboost算法和视觉显著性的羊只目标检测与计数方法研究[D]. 杨凌: 西北农林科技大学, 2019.
[34]	付忠良. 关于AdaBoost有效性的分析[J]. 计算机研究与发展, 2008, 45(10): 1747-1755.
[35]	LIANG X, XU C, SHEN X, et al. Human parsing with contextualized convolutional neural network[J]. IEEE T Pattern Anal, 2017, 39(1): 115-127. doi: 10.1109/TPAMI.2016.2537339
[36]	卢伟, 胡海阳, 王家鹏, 等. 基于卷积神经网络面部图像识别的拖拉机驾驶员疲劳检测[J]. 农业工程学报, 2018, 34(7): 192-199.

Cited By

Get Citation

PDF

XML

Article views (1227) PDF downloads (1947)

Turn off MathJax

Article Contents

Abstract

References

Study on distribution map of weeds in rice field based on UAV remote sensing

Abstract

References

Catalog

Export File

Citation

Format

Content