Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (5): 1127-1135    DOI: 10.11873/j.issn.1004-0323.2020.5.1127
遥感应用     
南方地区复杂条件下的耕地面积遥感提取方法
牟昱璇1(),邬明权2(),牛铮2,黄文江3,杨尽1
1.成都理工大学旅游与城乡规划学院,四川 成都 610059
2.中国科学院空天信息创新研究院遥感科学国家重点实验室,北京 100101
3.中国科学院空天信息创新研究院数字地球重点实验室,北京 100101
Method of Remote Sensing Extraction of Cultivated Land Area under Complex Conditions in Southern Region
Yuxuan Mu1(),Mingquan Wu2(),Zheng Niu2,Wenjiang Huang3,Jin Yang1
1.College of Tourism and Urban-Rural Planning,Chengdu University of Technology,Chengdu 610059,China
2.State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China
3.Key Laboratory of Digital Earth Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101
 全文: PDF(4172 KB)   HTML
摘要:

针对我国南方地区植被类型复杂、地形复杂和地块破碎等原因导致耕地信息提取精度较低问题,提出了一种面向对象和CART决策树结合的复杂条件下耕地面积提取方法。以广西南宁市隆安县与武鸣县地区为研究区,采用Sentinel-2A影像,结合数字高程数据(Digital Elevation Model,DEM)及归一化植被指数(Normalized Difference Vegetation Index,NDVI)等多源数据,利用面向对象分割技术识别地块信息,然后以地块为单位采用CART(Classification And Regression Tree,CART)决策树分类法,依据不同地类的形状、光谱特征,提取研究区的耕地。结果表明:面向对象的CART决策树分类方法分类总体精度和Kappa系数分别为96.1%和0.94,相比较于未加入面向对象分割的CART决策树耕地信息提取总体精度提高Kappa系数提高0.54,面向对象的分割方法有利于减少复杂背景对耕地提取的影响。基于面向对象的CART决策树分类方法相比较于传统方法对研究区耕地信息的提取有较好的精确性,能够提高耕地信息的提取精度。

关键词: Sentinel-2A面向对象CART决策树分类耕地提取    
Abstract:

In order to solve the problems of low precision of cultivated land information extraction due to complex vegetation types, complex terrain and broken plots in southern China, a method of arable land area extraction under complex conditions of object-oriented and cart decision tree is proposed. Taking Longan County and Wuming County of Nanning City, Guangxi as the study area, using Sentinel-2A image, combining digital elevation data DEM and normalized vegetation index NDVI and other multi-source data, using object-oriented segmentation technology to identify plot information, and then using CART decision tree classification method, according to the shape and spectral characteristics of different land types, the cultivated land in the study area is extracted. The results show that the overall precision and Kappa coefficient of the object-oriented CART decision tree classification method are 96.1% and 0.94, respectively. Compared with the total accuracy of cultivated land information extraction of cart decision tree without object-oriented segmentation, the kappa coefficient is increased by 0.54. The object-oriented segmentation method is beneficial to reducing the influence of complex background on the extraction of cultivated land. Based on the object-oriented CART decision tree classification method, the extraction of the cultivated land information in the research area is better than the traditional method, and the extraction precision of the cultivated land information can be improved.

Key words: Sentinel-2A    Object-oriented    CART decision tree classification    Farmland extraction
收稿日期: 2019-10-16 出版日期: 2020-11-26
ZTFLH:  TP79  
基金资助: 中国科学院A类战略性先导科技专项“地球大数据科学工程”(XDA19030304);中国科学院青年创新促进会(2017089)
通讯作者: 邬明权     E-mail: myanoyui@163.com;wumq@aircas.ac.cn
作者简介: 牟昱璇(1993-),女,新疆乌鲁木齐人,硕士研究生,主要从事农业遥感和生态遥感研究。E?mail: myanoyui@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
牟昱璇
邬明权
牛铮
黄文江
杨尽

引用本文:

牟昱璇,邬明权,牛铮,黄文江,杨尽. 南方地区复杂条件下的耕地面积遥感提取方法[J]. 遥感技术与应用, 2020, 35(5): 1127-1135.

Yuxuan Mu,Mingquan Wu,Zheng Niu,Wenjiang Huang,Jin Yang. Method of Remote Sensing Extraction of Cultivated Land Area under Complex Conditions in Southern Region. Remote Sensing Technology and Application, 2020, 35(5): 1127-1135.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.5.1127        http://www.rsta.ac.cn/CN/Y2020/V35/I5/1127

图1  研究区位置
图2  技术流程
图3  不同分割尺度效果对比
图4  CART决策树分类规则
图5  分类结果对比
分类方法总体 精度/%Kappa系数类别生产者精度 /%用户精度 /%
面向对象的CART决策树分类法96.10.94耕地92.293.3
建设用地96.285.3
林地97.499.2
水体96.599.5
CART决策树分类法决策树71.00.40耕地66.599.8
建设用地98.658.9
林地99.819.2
水体100.0100.0
土地覆盖产品72.90.46耕地76.494.8
建设用地49.450.0
林地97.630.2
水体78.198.5
表1  不同分类方法的耕地分类精度
图6  研究区西部林地主导区域分类结果细节对比
图7  本文分类结果与土地覆盖产品数据以及影像数据的部分区域对比
1 Wu M Q, Huang W J, Niu Z, et al. Validation of Synthetic Daily Landsat NDVI Time Series Data Generated by The Improved Spatial and Temporal Data Fusion Approach[J].Information Fusion, 2018, 40:34-44.doi:/10.1016/j.inffus.2017. 06.005.
doi: /10.1016/j.inffus.2017. 06.005
2 Denize J, Hubert-Moy L, Betbeder J, et al. Evaluation of Using Sentinel-1 and -2 Time-series to Identify Winter Land Use in Agricultural Landscapes[J].Remote Sensing, 2019,11(1):37.doi:/10.3390/rs11010037.
doi: /10.3390/rs11010037
3 Shi Y, Lou Y, Zhang Z, et al. Estimation of Methane Emissions based on Crop Yield and Remote Sensing Data in a Paddy Field[J].Greenhouse Gases:Science and Technology, 2020,10(1):196-207.doi:/10.1002/ghg.1946.
doi: /10.1002/ghg.1946
4 Aguilar M A, Saldaña M M, Aguilar F J, et al. GeoEye-1 and WorldView-2 Pan-Sharpened Imagery for Object-based Classification in Urban Environments[J].International Journal of Remote Sensing, 2013, 34(7):2583-2606.doi:/10.1080/01431161.2012.747018.
doi: /10.1080/01431161.2012.747018
5 Vieira M A, Formaggio A R, Rennó C D, et al. Object based Image Analysis and Data Mining Applied to A Remotely Sensed Landsat Time-Series to Map Sugarcane over Large Areas[J].Remote Sensing of Environment, 2012, 123(8):553-562.doi:/10.1016/j.rse.2012.04.011.
doi: /10.1016/j.rse.2012.04.011
6 Lewisgonzales S L. Accuracy of Supervised Classification of Cropland in Sub-Saharan Africa[D].Knoxville:University of Tennessee.2015.
7 Wang Lianxi, Zhang Ting, Li Qi, et al. Decision Tree Classification for Extraction of Ningxia Multiple Cropping Index[J].Remote Sensing Information, 2018,33(1):45-50.
7 王连喜,章婷,李琪,等.决策树分类提取宁夏耕地复种指数[J].遥感信息,2018,33(1):45-50.
8 Gong P, Liu H, Zhang M N, et al. Stable Classification with Limited Sample: Transferring a 30 m Resolution Sample Set Collected in 2015 to Mapping 10 m Resolution Global Land Cover in 2017[J].Science Bulletin,2019,64(6):370-373.
9 Hao Shuang, Chen Yongfu, Liu Hua, et al. Object-oriented Forest Classification of Linzhi County based on CART Decision Tree with Texture Information [J].Remote Sensing Technology and Application ,2017,32(2):386-394.
9 郝泷,陈永富,刘华等.基于纹理信息CART决策树的林芝县森林植被面向对象分类[J].遥感技术与应用,2017,32(2):386-394.
10 Lili Lü, Xie Yaowen, Huang Xiaojun, et al. Desertification Information Extraction Method Research based on The CART Decision Tree Classification[J].Remote Sensing Technology and Application, 2017, 32(3):499-506.
10 吕利利,颉耀文,黄晓君,等.基于CART决策树分类的沙漠化信息提取方法研究[J].遥感技术与应用,2017,32(3):499-506.
11 Zhang Tianzhu, Zhang Fengrong, Huang Jingwen, et al. Spatial Pattern Evolution of Abandoned Arable Land Its Influencing Factor in Industrialized Region[J].Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(2):146-152.
11 张天柱,张凤荣,黄敬文等.工业化区域撂荒耕地空间格局演变及影响因素分析[J].农业工程学报,2019,35(15):246-255.
12 Sun Jianwei, Wang Chao, Wang Na, et al. Research on Land Use Classification Monitoring through the Remote Sensing Data of ZY-3 Satellite based on CART Decision Tree [J].Journal of Central China Normal University, 2016,50(6):937-943.
12 孙建伟,王超,王娜,等.基于CART决策树的ZY-3卫星遥感数据土地利用分类监测[J].华中师范大学学报(自然科学版),2016,50(6):937-943.
13 Benz U. Definiens Imaging GmbH: Object-Oriented Classification and Feature Detection[J].IEEE Geo-science and Remote Sensing Society Newsletter. 2001(5):16-20.
14 Xu Shiwu, Yang Shuang, Sun Fei, et al. Method Research on Cultivated Land Extraction based on Object One-class Classification of High-spatial-resolution Image [J],Bulletin of Surveying and Mapping, 2014(10):78-81.徐世武,杨双,孙飞,等.面向对象的高分辨率影像单值分类耕地提取方法研究[J].测绘通报,2014(10):78-81.
15 Wang Xinjun, Wu Hongqi, Sheng Jiandong, et al. Object-oriented Farmland Extraction from High Spatial Resolution Imagery [J].Xinjiang Agricultural Sciences ,2012,49(2):371-378.
15 王新军,武红旗,盛建东,等.面向对象的高分辨率影像耕地信息提取[J].新疆农业科学,2012,49(2):371-378.
16 Ouyang Tao, Liu Zhenhua, Xiao Beisheng, et al. Based on ICA Object-Oriented Farmland Extraction [J].Jiangsu Agricultural Sciences ,2016,44(7):372-376.
16 欧阳涛,刘振华,肖北生,等.基于ICA面向对象的耕地信息提取[J].江苏农业科学,2016,44(7):372-376.
17 Ren Chuanshuai, Huang Wenjiang, Ye Huichun, et al. Extraction of Banana Orchards based on GF-2 Satellite Imagery and Its Accuracy Analysis[J].Remote Sensing Information, 2017,32(6):78-84.
17 任传帅,黄文江,叶回春,等. 利用高分二号数据提取香蕉林信息及精度分析[J]. 遥感信息, 2017,32(6):78-84.
18 Xu Chao, Zhang Jinrui, Pan Yaozhong, et al. Extraction of Cropland Information based on Multi-temporal TM Images[J].Remote Sensing for Land & Resources, 2013, 25(4):166-173.
18 徐超, 詹金瑞, 潘耀忠,等. 基于多时相TM图像的耕地信息提取[J]. 国土资源遥感, 2013, 25(4):166-173.
19 Tong Xinhua, Mao Beiqun, Wei Yanfei, et al. Extraction of Cultivated Land Using Objected-Oriented Classification Method based on MODIS-NDVI Time Series Data[J].Journal of Guangxi Teachers Education University:Natural Science Edition, 2017(4):98-106.童新华, 毛碑裙, 韦燕飞,等. 基于MODIS-NDV I时序数据集的面向对象分类提取广西耕地面积的方法研究[J]. 广西师范学院学报(自然科学版), 2017(4):98-106.
20 Wu M Q, Yang C H, Song X Y, et al. Monitoring Cotton Root Rot by Synthetic Sentinel-2 NDVI Time Series Using Improved Spatial and Temporal Data Fusion[J].Scientific Reports, 2018,8(1):2016.doi:/10.1038/s41598-018-20156-z.
doi: /10.1038/s41598-018-20156-z
21 Ma Yangyang, Zhang Caixia, Zhang Jichao, et al. Research on Object-oriented Classification Method Assisted with NDVI/DEM in ExtractingCassava:Taking Wuming County for Example[J].Geography and Geo-Information Science,2015,31(1):49-53.
21 马洋洋, 张彩霞, 张继超, 等. 辅以 NDVI/DEM 的面向对象木薯提取方法研究——以广西壮族自治区武鸣县为例[J]. 地理与地理信息科学, 2015, 31(1): 49-53.
22 Opitz D, Blundell S. Object Recognition and Image Segmentation: The Feature Analyst® Approach[M].Object-based Image Analysis. Springer, Berlin, Heidelberg, 2008: 153-167.
23 Shi Peirong, Chen Yongfu, Liu Hua, et al. Optimized Methodology for Classification of Remote Sensing Images based on Object-oriented:Applicatication to the Typical Forest of Milin in Tibet [J].Remote Sensing Technology and Application,2017,32(3):466-474.
23 施佩荣,陈永富,刘华,等.基于改进的面向对象遥感影像分类方法研究——以西藏米林县典型林区为例[J].遥感技术与应用,2017,32(3):466-474.
24 Tang Z W, Wang H, Li X B, et al. An Object-based Approach for Mapping Crop Coverage Using Multiscale Weighted and Machine Learning Methods[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 1700-1713.doi:10.1109/JSTARS. 2020. 2983439.
doi: 10.1109/JSTARS. 2020. 2983439
25 Li Zhongyuan, Wu Bingfang, Zhang Miao, et al. Identifying Rapeseed Planting Area Using an Object-oriented Method and Crop Phenology[J].Geography and Geo-Information Science, 2019,21(5):720-730.
25 李中元,吴炳方,张淼,等.利用物候差异与面向对象决策树提取油菜种植面积[J].地球信息科学学报,2019,21(5):720-730.
26 Wang Haijun, Le Chengfeng. Extraction of Paddy Field Using Objects-Oriented Fuzzy Classification Approach based on Texture Characteristic[J].Geography and Geo-Information Science, 2008, 24(5):40-43.
26 王海君, 乐成峰. 应用基于纹理的面向对象分类模糊方法提取水田信息[J]. 地理与地理信息科学, 2008, 24(5):40-43.
27 Li Xiaohui, Wang Hong, Li Xiaobing, et al. Study on Crops Remote Sensing Classification based on Multi-Temporal Landsat 8 OLI Images[J].Remote Sensing Technology and Application, 2019,34(2):389-397.
27 李晓慧,王宏,李晓兵,等.基于多时相Landsat 8 OLI影像的农作物遥感分类研究[J].遥感技术与应用,2019,34(2):389-397.
28 Ma Yulong Lin Zhilei. Wetland Change Detection based on Object-oriented and CART Decision Tree Method——A Case Study of Wetlands in Longxiang Island[J].Fujian Normal University:Natural Science Edition, 2017(6):74-85.马宇龙, 林志垒. 基于面向对象和CART决策树方法的遥感影像湿地变化检测研究——以龙祥岛地区为例[J]. 福建师范大学学报(自然科学版), 2017(6):74-85.
29 Hao Jiannan. Application of Texture Enhancement Extraction and Object-oriented High-resolution Image Classification[D].Nanchang: East China University of Technology,2018.
29 郝剑南. 纹理增强提取与面向对象结合的高分影像分类的应用[D].南昌:东华理工大学,2018.
30 Wang Yongmei,Yang Chuanjun,Deng Nanrong. Reasonability Validation on Field Ridge Coefficient based on Remote Sensing Image[J].Journal of Anhui Agricultural Sciences,2010,38(17):9292-9294,9360.
30 王永梅,杨传俊,邓南荣.基于遥感影像的田坎系数的合理性验证——以韶关乐昌市为例[J].安徽农业科学,2010,38(17):9292-9294,9360.
[1] 郑琪,邸苏闯,潘兴瑶,刘洪禄,朱永华,张岑,周星. 基于Rapid Eye数据的北京生态涵养区土地利用分类及变化研究[J]. 遥感技术与应用, 2020, 35(5): 1118-1126.
[2] 李宏达,高小红,汤敏. 基于CNN的不同空间分辨率影像土地覆被分类研究[J]. 遥感技术与应用, 2020, 35(4): 749-758.
[3] 连喜红,祁元,王宏伟,张金龙,杨瑞. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4): 775-785.
[4] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[5] 郝睿,李兆富,张舒昱,潘剑君,姜小三,张文敏,宋金超. 整合无人机和面向对象的农村居住环境信息提取[J]. 遥感技术与应用, 2020, 35(3): 576-586.
[6] 王芳,杨武年,王建,谢兵,任金铜. 遥感影像多尺度分割中最优尺度的选取及评价[J]. 遥感技术与应用, 2020, 35(3): 623-633.
[7] 李强,冯德俊,瑚敏君,伍燚垚,杨历辉. 集成特征分量的高分二号影像阴影检测[J]. 遥感技术与应用, 2019, 34(6): 1252-1260.
[8] 徐凡, 张雪红, 石玉立. 基于激光雷达和航拍影像的城市地物分类研究[J]. 遥感技术与应用, 2019, 34(2): 253-262.
[9] 刘立, 刘勇. 基于优化分割分类层次体系的土地覆被分类制图方法探讨[J]. 遥感技术与应用, 2019, 34(1): 79-89.
[10] 程凯, 王卷乐, Jaahanaa Davaadorj, 韩雪华. 近30 a来蒙古国乌兰巴托市城镇扩张及其驱动力分析[J]. 遥感技术与应用, 2019, 34(1): 90-100.
[11] 高书鹏, 史正涛, 刘晓龙, 柏延臣. 基于高时空分辨率可见光遥感数据的热带山地橡胶林识别[J]. 遥感技术与应用, 2018, 33(6): 1122-1131.
[12] 李哲, 宫兆宁, 刘先林, 关晖, 王颖. 基于面向对象多端元混解模型的植被覆盖度反演及其时空分布研究[J]. 遥感技术与应用, 2018, 33(6): 1149-1158.
[13] 韩涛, 潘剑君, 张培育, 曹罗丹. Sentinel-2A与Landsat-8影像在油菜识别中的差异性研究[J]. 遥感技术与应用, 2018, 33(5): 890-899.
[14] 闫鹏飞,明冬萍. 尺度自适应的高分辨率遥感影像分水岭分割方法[J]. 遥感技术与应用, 2018, 33(2): 321-330.
[15] 江东,陈帅,丁方宇,付晶莹,郝蒙蒙. 基于面向对象的遥感影像分类研究——以河北省柏乡县为例[J]. 遥感技术与应用, 2018, 33(1): 143-150.