基于不同分类器的农用地分类提取

doi:10.6048/j.issn.1001-4330.2019.08.022

新疆农业科学 ›› 2019, Vol. 56 ›› Issue (8): 1560-1568.DOI: 10.6048/j.issn.1001-4330.2019.08.022

• 土壤肥料·微生物·植物保护·畜牧兽医·信息技术 • 上一篇

基于不同分类器的农用地分类提取

张峰¹, 赵忠国², 李刚¹, 陈刚³

1.新疆交通职业技术学院,乌鲁木齐, 830052;
2.新疆大学资源与环境科学学院,乌鲁木齐,830052;
3.河南测绘职业学院,郑州,450000

收稿日期:2019-05-29 出版日期:2019-08-20 发布日期:2019-10-10
通信作者: 李刚(1974-),男,副教授,新疆米泉人,研究方向为软件工程,(E-mail)55071406@qq.com
作者简介:张峰(1982-),男,河南商丘人,博士研究生,研究方向为遥感与地理信息系统,(E-mail)erajps@163.com
基金资助:
新疆维吾尔自治区自然科学基金项目"构建大面积农田遥感监测系统关键技术研究"(2016D01B016)

Study on Classification and Extraction of Agricultural Land in Qitai County of Xinjiang Based on Different Classifiers

ZHANG Feng¹, ZHAO Zhong-guo², LI Gang¹, CHEN Gang³

1.Xinjiang Vocational and Technical College of Communications, Xinjiang Uygur Autonomous Region, Urumqi, 830052;
2. College of Resources and Environmental Sciences, Xinjiang University, Xinjiang Uygur Autonomous Region, Urumqi, 830052;
3. Henan Vocational College of Surveying and Mapping, Henan, Zhengzhou, 450000

Received:2019-05-29 Online:2019-08-20 Published:2019-10-10
Correspondence author: LI Gang(1974-),Male, native place: Miquan, Xinjiang. Associate professor, research filed: software engineering.(E-mail)55071406@qq.com
Supported by:
Supported by: The Natural Science Foundation of Xinjiang Uygur Autonomous Region Project "Research on Key Technologies of Establishing Remote Sensing Monitoring System for Large Area Farmland"(2016D01B016)

摘要/Abstract

摘要： 【目的】分析Landsat 8 OLI卫星遥感影像数据面向农用地分类的实际应用方法和效果,以新疆奇台县南部为研究对象。【方法】使用随机森林(RF)、支持向量机(SVM)和神经网络(Neural Net)三种分类器进行研究区农用地分类对比。【结果】通过对三种分类器参数设置参数精度检验,利用上述三种算法对农用地地物分类进行精度评价,在整体分类精度中,支持向量机算法(SVM)<随机森林算法(RF)<神经网络算法(Neural Net),分类精度分别为:90.75%,94.30%和94.84%。【结论】神经网络方法(Neural Net)在该地区的农用地物整体分类上,比支持向量机(SVM)和随机森林法(RF)相比具有一定的优势,并获得较好的分类精度。

关键词: 农用地; 神经网络; 支持向量机; 随机森林; 信息提取

Abstract: 【Objective】 Classification based on remote sensing image is one of the important contents of remote sensing data application. How to improve the classification accuracy of remote sensing image is the key of remote sensing image research. 【Method】In order to analyze the practical application method and effect of Landsat 8 OLI satellite remote sensing image data for agricultural land classification, this paper takes the southern Qitai County of Xinjiang as the research object, and uses three classifiers, random forest (RF), support vector machine (SVM) and neural network (Neural Net), to conduct a comparative study of agricultural land classification in the study area. 【Result】Through the parameter setting accuracy test of the three classifiers, the accuracy of agricultural land classification is evaluated by using the above three algorithms. In the overall classification accuracy, the support vector machine algorithm (SVM) < random forest algorithm (RF) < neural network algorithm (Neural Net) has the classification accuracy of 90.75%, 94.30% and 94.84%, respectively. 【Conclusion】Neural Net has some advantages over Support Vector Machine (SVM) and Random Forest Method (RF) in the overall classification of agricultural land use in this area, and achieves better classification accuracy.

Key words: agricultural land; neural network; support vector machine; random forest; information extraction

中图分类号:

S159

张峰, 赵忠国, 李刚, 陈刚. 基于不同分类器的农用地分类提取[J]. 新疆农业科学, 2019, 56(8): 1560-1568.

ZHANG Feng, ZHAO Zhong-guo, LI Gang, CHEN Gang. Study on Classification and Extraction of Agricultural Land in Qitai County of Xinjiang Based on Different Classifiers[J]. Xinjiang Agricultural Sciences, 2019, 56(8): 1560-1568.

参考文献

[1] 杨超,邬国锋,李清泉,等.植被遥感分类方法研究进展[J],2018,34(4):24-32.
YANG Chao, WU Guo-feng,LI Qing-quan,et al.(2018).Research Progress on Remote Sensing Classification of Vegetation[J].Geography and Geo-information Science ,34(4):24-32.(in Chinese)
[2] 郭航,张晓丽. 基于遥感技术的植被分类研究现状与发展趋势[J], 2007, 20(3): 14-19.
GUO Hang, ZHANG Xiao-li.(2007).Current Status and Developing Trend in Vegetation Classification Based on RS Technology[J]. WORLD FORESTRY RESEARCH ,20(3): 14-19.(in Chinese)
[3]刘毅,杜培军,郑辉,等. 基于随机森林的国产小卫星遥感影像分类研究[J],2012, 37(4): 194-196.
LIU Yi,DU Pei-jun,ZHENG Hui,et al .(2012). Classification of China small satellite remote sensing image based on random forests[J]. Science of Surveying and Mapping, 37(4): 194-196.(in Chinese)
[4] 张锐. 基于改进支持向量机的盐碱地信息精确提取方法研究[J]. 灌溉排水学报,2018, 37(9):62-68.
ZHANG Rui. (2018).An Improved Support Vector Machine Method for Estimating Saline-alkali Soil from Remote Sensing Imagery [J]. Journal of Irrigation and Drainage, 37(9):62-68.(in Chinese)
[5]徐浩田. 基于支持向量机的湿地遥感分类及生态系统健康评价研究[D].沈阳:沈阳农业大学硕士论文,2017.
XU Hao-tian.(2014). Study on the wetland remote sensing classification and ecosystem health evaluation based on support vector machine [D].Master Disseration.Shen-yang agricultural university,Shenyang.(in Chinese)
[6]张浩,赵云胜,陈冠宇,等.基于支持向量机的遥感图像建筑物识别与分类方法研究[J].地质科技情报,2016,35(6):18-24.
ZHANG Hao,ZHAO Yun-sheng,CHEN Guan-yu ,et al.(2016). Remote Sensing Image Building Recognition and Classification Based on the Support Vector Machine[J]. Geological Science and Technology Inforamtion, 35(6):18-24.(in Chinese)
[7]陈芳.基于支持向量机的高分辨率遥感影像的舰船目标识别研究[J].船舶科学技术,2017,39(12A):180-183.
CHEN Fang.(2017). Research on Ship Target Recognition Based on High Resolution Remote Sensing Image of Support Vector Machine [J]. Ship Science and Technology, 39(12A):180-183.(in Chinese)
[8]程彬. 基于支持向量机的乾安县土地利用遥感分类研究[J]. 长春师范大学学报, 2017, 36(6):86-88.
CHENG Bin.(2017). Land Use Information Extraction Based on Support Vector Machine Using Multitemporal Remote Sensing in Qian'an County[J]. Journal of Changchun Normal University(Natural Science), 36(6):86-88.(in Chinese)
[9]Rodriguez-Galiano, V. F, Ghimire ,B, Rogan, J. et al. (2012).An assessment of the effectiveness of a random forest classifier for land-cover classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,67:93-104.
[10]Miao, X, Heaton, J, S, Zheng,S, et al. (2012 ). Applying tree-based ensemble algorithms to the classification of ecological zones using multi-temporal multi-source remote-sensing data[J].International Journal of Remote Sensing,33(6):1,823-1,849.
[11]Clark,M.L, Roberts,D.A.(2012) .Species-level differences in hyperspectral metrics among tropical rainforest tress as determined by a tree-based classifier[J].Remote Sensing,4(6):1,820-1,855.
[12]Pierce,A .D,Farris,C.A ,Taylor, A .H.(2012). Use of random forests for modeling and mapping forest canopy fuels for fire behavior analysis in Lassen Volcanic National Park, California USA[J].Forest Ecology and management,279:77-89.
[13]李垒,任越美.基于随机森林的高光谱遥感图像分类[J]. 计算机应用研究,2016,52(54):189-195.
LI Lei, REN Yue-mei.(2016). Classification of hyperspectral data based on random forest[J]. Computer Engineering and Applications, 52(54):189-195.(in Chinese)
[14]郭玉宝,池天河,彭玲,等. 利用随机森林的高分一号遥感数据进行城市用地分类[J].测绘通报,2016, (5):73-76.
GUO Yu-bao,CHI Tian-he,PENG Ling, et al.(2016).Classification of GF-1 Remote Sensing Image Based on Random Forests for Urban Land-use[J].Bulletin of Surveying and Mapping, (5):73-76.(in Chinese)
[15]张锦水,何春阳 ,潘耀忠 ,等. 基于SVM的多源信息复合的高空间分辨率遥感数据分类研究 [J]. 2006, 10(1): 49-57.
ZHANG Jin-shui,HE Chun-yang,PAN Yao-zhong, et al. (2006). The High Spatial Resolution RS Image Classification Based on SVM Method with the Multi-Source Data[J]. Journal of Remote Sensing Journal of Remote Sensing. 10(1): 49-57.(in Chinese)
[16]冯恒栋.基于人工神经网络和模糊分类的森林植被遥感图像分类研究[D].沈阳,东北师范大学,2009.
FENG Heng-dong.(2009).Classification of Forest Vegetation Remote Sensing Images Based on Artificial Neural Network and Fuzzy Classification [D].Master Disseration. Shen yang normal university, Shenyang.(in Chinese)
[17] 陈祎荻,秦玉平. 基于机器学习的文本分类方法综述[J], 渤海大学学报(自然科学版), 2010, 31(2): 201-205.
CHEN Yi-di,QIN Yu-ping.(2010). Review on text categorization methods based on machine learning[J]. Journal of Bohai University(Natural Science Edition), 31(2): 201-205.(in Chinese)
[18] 都业军,周肃,方吉宙,等. 人工神经网络在遥感影像分类中的应用与对比研究[J],测绘科学,2010, (S1),120-121,51.
DU Ye-Jun, ZHOU Su, FANG Ji-zhou, et al. (2010). Application and Contrast Research on Remote Sensing Image Classification Based on Artificial Neural Network[J], Science of Surveying and Mapping, (S1),120-121,51. (in Chinese)
[19] 闫琰,董秀兰,李燕. 基于ENVI的遥感图像监督分类方法比较研究[J]. 北京测绘, 2011, (3): 14-16.
YAN Yan, DONG Xiu-lan, LI Yan. (2011). The Comparative Study of Remote Sensing Image Supervised Classification Methods Based on ENVI[J] Beijing Surveying and Mapping, (3): 14-16. (in Chinese)

基于不同分类器的农用地分类提取

Study on Classification and Extraction of Agricultural Land in Qitai County of Xinjiang Based on Different Classifiers

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	方杰, 张杰, 马娟, 田翔, 于秀针, 冯斌. 基于神经网络PID算法的优化饲料配制系统[J]. 新疆农业科学, 2023, 60(4): 1003-1010.
[2]	吕金城, 王振锡, 杨勇强, 曲延斌, 马琪瑶. 基于WorldView-2影像和随机森林算法的天山云杉蓄积量反演[J]. 新疆农业科学, 2022, 59(8): 1992-1998.
[3]	韩坤林, 王钊英, 杨会民, 陈毅飞, 蒋永新, 张佳喜. 基于PCA-BPNN的温室番茄果实直径预测模型[J]. 新疆农业科学, 2022, 59(2): 485-492.
[4]	雷声渊, 马本学, 王文霞, 罗秀芝, 李玉洁, 戴建国. 基于微调卷积神经网络迁移学习模式下被害棉叶图像的识别[J]. 新疆农业科学, 2019, 56(7): 1294-1302.
[5]	罗秀芝, 马本学, 李小霞, 胡洋洋, 王文霞, 雷声渊. 基于卷积神经网络干制哈密大枣纹理分级[J]. 新疆农业科学, 2018, 55(12): 2220-2227.
[6]	范中建,朱荣光,张凡凡,姚雪东,邱园园,阎聪. 基于BP和Adaboost-BP神经网络的羊肉新鲜度高光谱定性分析[J]. 新疆农业科学, 2018, 55(1): 183-188.
[7]	黄华;蔡仁;努尔古丽·艾力;穆振侠. 基于ARIMA和GA-Elman神经网络的新疆年降水耦合预测研究[J]. , 2015, 52(6): 1093-1098.
[8]	廖享;高晶;唐军;符继红. 基于气质的主成分支持向量基对新疆薰衣草精油判别分析[J]. , 2014, 51(7): 1367-1372.
[9]	买买提·沙吾提;塔西甫拉提·特依拜;丁建丽;张飞. BP神经网络在渭干河流域土壤盐渍化预测中的应用[J]. , 2013, 50(4): 774-779.
[10]	蔡洪江;司马义·努尔拉;张苏莉;杨家龙;买买提江·依米提. 农用地膜自然老化与人工老化相关性的研究[J]. , 2010, 47(8): 1580-1583.
[11]	刘新平;吕晓. 新疆农用地利用效益及其区域间差异性分析[J]. , 2009, 46(2): 419-424.
[12]	王雪梅;柴仲平;龚爱谨;塔西甫拉提·特依拜. BP神经网络算法在土地覆盖分类中的应用研究——以新疆于田绿洲为例[J]. , 2009, 46(1): 142-146.
[13]	张芳;塔西甫拉提·特依拜;丁建丽. 基于FHSI影像融合技术的绿洲干旱区农田信息提取研究[J]. , 2008, 45(2): 270-275.
[14]	朱春江;唐德善. 基于BP神经网络和D-S理论的塔里木河输水目标预报研究[J]. , 2006, 43(2): 156-158.
[15]	朱春江;唐德善. 基于BP神经网络的塔里木河月流量预报研究[J]. , 2005, 42(4): 210-214.