[1]宋恩泽,张颖,邵光成,等.基于无人机多光谱遥感的农业园区地物分类研究[J].江苏农业学报,2023,(09):1862-1871.[doi:doi:10.3969/j.issn.1000-4440.2023.09.008]
　SONG En-ze,ZHANG Ying,SHAO Guang-cheng,et al.Classification of geological features in agricultural parks based on multispectral remote sensing by unmanned aerial vehicle[J].,2023,(09):1862-1871.[doi:doi:10.3969/j.issn.1000-4440.2023.09.008]
点击复制

基于无人机多光谱遥感的农业园区地物分类研究()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年09期
页码:
1862-1871
栏目:
农业信息工程
出版日期:
2023-12-31

文章信息/Info

Title:
Classification of geological features in agricultural parks based on multispectral remote sensing by unmanned aerial vehicle
作者:
宋恩泽1; 张颖2; 邵光成1; 刘杰3; 王羿1; 朱雪颖4
(1.河海大学农业科学与工程学院,江苏南京210098；2.南京市江宁区水务局,江苏南京211100；3.天津市灌溉排水中心,天津300074；4.西安理工大学水利水电学院,陕西西安710048)
Author(s):
SONG En-ze1; ZHANG Ying2; SHAO Guang-cheng1; LIU Jie3; WANG Yi1; ZHU Xue-ying4
(1.College of Agricultural Science and Engineering, Hohai University, Nanjing 210098, China;2.Water Resources Bureau of Jiangning Area in Nanjing City, Nanjing 211100, China;3.Tianjin Irrigation and Drainage Center, Tianjin 300074, China;4.College of Water Resources and Hydropower, Xi′an University of Technology, Xi′an 710048, China)
关键词:
无人机遥感; 农业园区; 地物分类
Keywords:
unmamed aerial vehicle remote sensing; agricultural park; classification of features
分类号:
S29
DOI:
doi:10.3969/j.issn.1000-4440.2023.09.008
文献标志码:
A
摘要:
复杂地物的快捷精准监测是遥感的热点和难点。为实现农业园区复杂地物的快捷准确分类监测,本研究以河海大学江宁校区节水园区为例,基于无人机多光谱遥感影像,分别采用支持向量机模型(SVM)、随机森林模型(RF)和人工神经网络模型(ANN)对试验区内地物进行精细分类,构建验证集混淆矩阵,并根据总体分类精度、Kappa系数等指标筛选出中小型农业园区的最适地物分类模型,并利用TensorFlow训练深度学习算法对最适分类模型的分类结果进行进一步优化。结果表明:SVM分类模型对试验农业园区的总体分类精度为97.4%,Kappa系数为0.96,优于RF、ANN分类模型；与原始SVM分类模型的分类结果相比,通过TensorFlow训练深度学习算法优化,将试验农业园区图像裁剪为a、b两区,a、b两区的分类精度分别为97.54%和99.12%,获得了较高的优化结果。研究结果可为中小型农业园区地物分类提供技术支持。
Abstract:
Fast and accurate monitoring of complex objects is a hot and difficult point in remote sensing. In order to realize the fast and accurate monitoring of complex feature classification in agricultural parks, this study took the water-saving park of Jiangning Campus of Hohai University as an example. Based on the multi-spectral remote sensing image of unmanned aerial vehicle (UAV), the support vector machine model (SVM), random forest model (RF) and artificial neural network model (ANN) were used to classify the objects in the test area, and the confusion matrix of the validation set was constructed. According to the overall classification accuracy, Kappa coefficient and other indicators, the optimal feature classification model of small and medium-sized agricultural parks was selected, and the TensorFlow training deep learning algorithm was used to further optimize the classification results of the optimal classification model. The results showed that the overall classification accuracy of SVM classification model was 97.4%, and the Kappa coefficient was 0.96, which was better than those of RF and ANN classification models. Compared with the original SVM classification model, the images of the experimental agricultural park were cut into a and b areas by TensorFlow training deep leaming algorithm optimization, and the classification accuracy of a and b areas was 97.54% and 99.12%, respectively and higher optimization results were obtained. The research results could provide technical support for the classification of small and medium-sized agricultural parks.

参考文献/References:

[1]马雷振. 国土空间规划背景下的现代农业产业园规划建设[J]. 河南农业,2023(13):31.
[2]韩文霆,郭聪聪,张立元,等. 基于无人机遥感的灌区土地利用与覆被分类方法[J]. 农业机械学报,2016,47(11):270-277.
[3]汪传建,赵庆展,马永建,等. 基于卷积神经网络的无人机遥感农作物分类[J]. 农业机械学报,2019,50(11):161-168.
[4]MAHDAVI S, SALEHI B, AMANI M, et al. A dynamic classification scheme for mapping spectrally similar classes: Application to wetland classification[J]. International Journal of Applied Earth Observation and Geoinformation,2019,83:101914.
[5]王柯,付怡然,彭向阳,等. 无人机低空遥感技术进展及典型行业应用综述[J]. 测绘通报,2017(S1):79-83.
[6]温昱婷,赵静,兰玉彬,等. 基于无人机可见光影像和面向对象的树种分类研究[J]. 西北林学院学报,2022,37(1):74-80,144.
[7]黄雨菲,路春燕,贾明明,等. 基于无人机影像与面向对象-深度学习的滨海湿地植物物种分类[J]. 生物多样性,2023,31(3):143-158.
[8]姜玉峰,齐建国,陈博伟,等. 基于无人机高光谱影像和机器学习的红树林树种精细分类[J]. 遥感技术与应用,2021,36(6):1416-1424.
[9]姚博,张怀清,刘洋,等. 面向对象CART决策树方法的湿地遥感分类[J]. 林业科学研究,2019,32(5):91-98.
[10]张静,王清茹,雷亚平,等. 基于机器学习和无人机图像的棉花密度识别研究[J]. 中国棉花,2021,48(9):6-10.
[11]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.
[12]BRYSON M, REID A, RAMOS F, et al. Airborne vision-based mapping and classification of large farmland environments[J]. Journal of Field Robotics,2010,27(5):632-655.
[13]杨蜀秦,宋志双,尹瀚平,等. 基于深度语义分割的无人机多光谱遥感作物分类方法[J]. 农业机械学报,2021,52(3):185-192.
[14]杨红艳,杜健民,阮培英,等. 基于无人机遥感与随机森林的荒漠草原植被分类方法[J]. 农业机械学报,2021,52(6):186-194.
[15]LOU P Q, FU B L, HE H C, et al. An optimized object-based random forest algorithm for marsh vegetation mapping using high-spatial-resolution GF-1 and ZY-3 data[J]. Remote Sensing,2020,12(8):1270.
[16]赵松,侯毅凯,张安兵,等. 基于无人机多光谱影像的滏阳河水质遥感反演[J]. 测绘与空间地理信息,2022,45(3):81-85.
[17]匡文慧,张树文,杜国明,等. 2015-2020年中国土地利用变化遥感制图及时空特征分析[J]. 地理学报,2022,77(5):1056-1071.
[18]赵静,李志铭,鲁力群,等. 基于无人机多光谱遥感图像的玉米田间杂草识别[J]. 中国农业科学,2020,53(8):1545-1555.
[19]陈琪,杨九艳,闫瑞玲,等. 荒漠区不同植被类型NDVI变化特征分析——以内蒙古阿拉善盟为例[J]. 中国草地学报,2022,44(3):17-28.
[20]BREIMAN L. Random forests[J]. Machine Learning,2001,45(1):5-32.
[21]杜尚海,古成科,张文静. 随机森林理论及其在水文地质领域的研究进展[J]. 中国环境科学,2022，42（9）:4285-4295.
[22]李垒,任越美. 基于随机森林的高光谱遥感图像分类[J]. 计算机工程与应用,2016,52(24):189-193.
[23]PHIRI D, MORGENROTH J, XU C. Four decades of land cover and forest connectivity study in Zambia-An object-based image analysis approach[J]. International Journal of Applied Earth Observation and Geoinformation,2019,79:97-109.
[24]修丽娜,刘湘南. 人工神经网络遥感分类方法研究现状及发展趋势探析[J]. 遥感技术与应用,2003(5):339-345.
[25]张海龙,蒋建军,吴宏安,等. SAR与TM影像融合及在BP神经网络分类中的应用[J]. 测绘学报,2006，35(3):229-233，239.
[26]VAPNIK V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks,1999,10(5):988-999.
[27]刘义志,赖华荣,张丁旺,等. 多特征混合核SVM模型的遥感影像变化检测[J]. 国土资源遥感,2019,31(1):16-21.
[28]景文龙,李博涵,杨守磊,等. 基于TensorFlow的均质数字岩心渗透率预测方法及应用[J]. 中国石油大学学报(自然科学版),2021,45(4):108-113.
[29]TANG W, HU J, ZHANG H. Kappa coefficient: a pupular measure rafer agreement[J]. Shanghai Archives of Psychiafry,2015,27(1):62-67.
[30]隋佳利. 二分类问题的支持向量机算法研究[D]. 曲阜:曲阜师范大学,2021.
[31]张驰,郭媛,黎明. 人工神经网络模型发展及应用综述[J]. 计算机工程与应用,2021,57(11):57-69.
[32]周开伟,钱雪忠,周世兵. 一种改进的多分类孪生支持向量机[J]. 计算机应用与软件,2022,39(4):269-274.

相似文献/References:

[1]郭铭淇,包云轩,黄璐,等.无人机多光谱影像在稻纵卷叶螟危害监测中的应用[J].江苏农业学报,2023,(07):1530.[doi:doi:10.3969/j.issn.1000-4440.2023.07.010]
　GUO Ming-qi,BAO Yun-xuan,HUANG Lu,et al.Application of multispectral image taken by unmanned aerial vehicle in monitoring Cnaphalocrocis medinalis Güenée damage on rice growth[J].,2023,(09):1530.[doi:doi:10.3969/j.issn.1000-4440.2023.07.010]

备注/Memo

备注/Memo:
收稿日期:2022-10-02基金项目:国家自然科学基金项目(51879072);江苏省水利科技项目(2015087)作者简介:宋恩泽(1999-),男,山西太原人,硕士研究生,主要从事农业遥感研究。(E-mali)1345532440@qq.com通讯作者:邵光成,(E-mali)sgcln@126.com
更新日期/Last Update: 2024-01-15