面向对象的特色农作物种植遥感调查方法研究

doi:10.12082/dqxxkx.2018.180116

地球信息科学学报 ›› 2018, Vol. 20 ›› Issue (10): 1509-1519.doi: 10.12082/dqxxkx.2018.180116

面向对象的特色农作物种植遥感调查方法研究

单治彬¹(), 孔金玲^2,^*(), 张永庭³, 李欢³, 关红³, 胡永新², 李健锋¹, 张文博¹

1. 长安大学地球科学与资源学院,西安 710054
2. 长安大学地质工程与测绘学院,西安 710054
3. 宁夏回族自治区遥感测绘勘查院,银川 750021

收稿日期:2018-02-28 修回日期:2018-07-19 出版日期:2018-10-25 发布日期:2018-10-17
通讯作者: 孔金玲 E-mail:zbshan_chd@126.com;jlkong@163.com
作者简介:
作者简介：单治彬（1993-）,男,陕西安康人,硕士生,主要从事遥感反演研究。E-mail: zbshan_chd@126.com
基金资助:
宁夏回族自治区重点研发计划项目（2016KJHM130）

Remote Sensing Investigation Method of Object-oriented Crops with Special Characteristics

SHAN Zhibin¹(), KONG Jinling²(), ZHANG Yongting³, LI Huan³, GUAN Hong³, HU Yongxin², LI Jianfeng¹, ZHANG Wenbo¹

1. School of Earth Science and Resources, Chang'an University, Xi'an 710054, China
2. School of geological engineering and Geomatics, Chang'an University, Xi'an 710054, China
3. The remote sensing surveying and Mapping Institute of the Ningxia Hui Autonomous Region, yinchuan 750021, China

Received:2018-02-28 Revised:2018-07-19 Online:2018-10-25 Published:2018-10-17
Supported by:
Key Research and Development Project of the Ningxia Hui Autonomous Region, No.2016KJHM130.

摘要/Abstract

摘要：

宁夏自治区具有土地、光能、引黄灌溉等优势,为宁夏特色农作物（硒砂瓜、枸杞、大枣）的生长提供了先天条件。快速准确地获取特色农作物的种植信息不仅是宁夏特色农作物监测、估产和灾害评估的重要依据,同时也是分析特色农作物结构分布变化和评价区域特色农业生产影响的重要凭证。近年来,随着航天技术和卫星传感器的不断发展,越来越多的学者将遥感技术运用到农作物种植信息的提取研究中。但是传统的遥感调查模型都是基于中低分辨遥感数据建立的,对于新的高分数据没有完备的信息提取模型。此外,基于GF-1遥感影像对类似宁夏特色农作物（硒砂瓜、枸杞、大枣）的信息提取研究相对较少,决策条件和分类模型的选择也难以满足高分农业的需求。基于此,本文利用国产GF-1 PMS遥感影像,在分析3类特色农作物光谱特征和纹理特征的基础上,建立了面向对象的支持向量机（SVM）分类模型,总体分类精度达到94.94%,Kappa系数为0.9174。同时将分类结果与传统的SVM分类结果相比较,研究发现面向对象的SVM模型的精度更高,效果最好,纹理信息的引入使光谱特征差异较小的枸杞和大枣更容易区分,有效降低了模型错分和漏分误差,改善了模型分类结果。研究结果为实现宁夏特色农作物的快速自动化提取提供了有效途径,也为开展农作物承保和受灾定损评估体系建设提供技术支撑。

关键词: 特色农作物, 支持向量机, 面向对象模型, 特征提取, GF-1影像

Abstract:

The advantages of Ningxia Hui Autonomous Region is land, light energy, and irrigation of Yellow River, which provides an inherent condition for the growth of characteristic crops of Ningxia (e.g. watermelon, Chinese wolfberry and jujube). Accessing to planting structure information of characteristic crops quicklf and accurately is not only an important basis for regional crop monitoring, yield estimation and disaster assessment, but also an important evidence for analyzing the spatial pattern changes of characteristic crop and assessing the impact of regional characteristics on agricultural production. In recent years, with the continuous development of space technology and remote sensing satellites, more and more scholars have applied remote sensing technology to the extraction of crop planting structure information. However, the traditional remote sensing survey model is only applicable to low resolution and medium resolution remote sensing data, and domestic and abroad scholars have relatively few studies on information extraction of similar Ningxia characteristic crops (e.g. watermelon, Chinese wolfberry and jujube), and the selection of classification models and strategies is difficult to meet the demand of rapid monitoring, accurate acquisition and real-time decision-making. Based on this, this paper calculate and analyze the spectral characteristics and texture features of the three types of specialty crops under the support of GF-2 remote sensing data, and establish an SVM of object-oriented classification model, the overall classification accuracy is 94.94% and the Kappa coefficient is 0.9174. And compare the classification results with the traditional SVM classification results, The study found that the SVM of object-oriented model established in this paper has the highest accuracy and best results, the texture information makes it easier to distinguish the Chinese wolfberry and jujube,whice has theless difference in spectral characteristics, and the texture information effectively reducing the model error and missing error, and improving the model classification results.

Key words: characteristic crops, support vector machine, object-oriented, feature extraction, GF-1 images

单治彬, 孔金玲, 张永庭, 李欢, 关红, 胡永新, 李健锋, 张文博. 面向对象的特色农作物种植遥感调查方法研究[J]. 地球信息科学学报, 2018, 20(10): 1509-1519.DOI:10.12082/dqxxkx.2018.180116

SHAN Zhibin,KONG Jinling,ZHANG Yongting,LI Huan,GUAN Hong,HU Yongxin,LI Jianfeng,ZHANG Wenbo. Remote Sensing Investigation Method of Object-oriented Crops with Special Characteristics[J]. Journal of Geo-information Science, 2018, 20(10): 1509-1519.DOI:10.12082/dqxxkx.2018.180116

图/表 10

图1

表1

图2

图3

图4

图5

图6

表2

表3

表4

参考文献 22

[1]	郭燕,武喜红,程永政等.用高分一号数据提取玉米面积及精度分析[J].遥感信息,2015,30(6):31-36. doi: 10.3969/j.issn.1000-3177.2015.06.006
	[ Guo Y, Wu X H, Chen Y Z,et al.Maize recognition and accuracy evaluation based on high resolution remote sensing (GF-1) data[J]. Remote Sensing Information, 2015,30(6):31-36. ] doi: 10.3969/j.issn.1000-3177.2015.06.006
[2]	Castillejo-González I L, López-Granados F, García-Ferrer A, et ac. Object- and pixel-based analysis for mapping crops and their agro-environmental associated measures using QuickBird inagery[J]. Computers and Electronics in Agriclture, 2009,68(2):207-215. doi: 10.1016/j.compag.2009.06.004
[3]	Witharana C, Civco D L, Meyer T H.Evaluation of data fusion and image segmentation in earth observation based rapid mapping workflows[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2014,87(2014):1-18.
[4]	Yang Shao, Ross S. Lunetta, Brandon Wheeler, et al.An evaluation of time-series smoothing algorithms for land-cover classifications using MODIS-NDVI multi-temporal data[J]. Remote Sensing of Environment, 2016,174:258-265. doi: 10.1016/j.rse.2015.12.023
[5]	刘佳,王利民,杨福刚,等.基于HJ时间序列数据的农作物种植面积估算[J].农业工程学报,2015,31(3):199-206. doi: 10.3969/j.issn.1002-6819.2015.03.026
	[ Liu J, Wang L M, Yang F G, et al.Remote sensing estimation of crop planting area based on HJ time-series images[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2015,31(3):199-206. ] doi: 10.3969/j.issn.1002-6819.2015.03.026
[6]	Kumar P, Gupta D K, Mishra V N, et al.Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data[J]. International Journal of Remote Sensing, 2015,36(6):1604-1617. doi: 10.1080/2150704X.2015.1019015
[7]	周艳飞,张绘芳,李霞,等.基于高分辨率遥感数据的胡杨与怪柳树冠提取[J].遥感技术与应用,2015,30(3):510-517. doi: 10.11873/j.issn.1004-0323.2015.3.0510
	[ Zhou Y F, Zhang H F, Li X, et al.Extraction of tree-crown of populus euphratica and tamarix ramosissima based on high resolution remote sensing data[J]. Remote Sensing Technology and Application, 2015,30(3):510-517. ] doi: 10.11873/j.issn.1004-0323.2015.3.0510
[8]	朴世龙,方精云,贺金生,等.中国草地植被生物量及其空间分布格局[J].植物生态学报,2004,28(4):491-498. doi: 10.17521/cjpe.2004.0067
	[ Piao S L, Fang J Y, He Jinsheng, et al.Spatial distribution of grassl and biomass in China[J]. Acta Phytoecologica Sinica, 2004,28(4):491-498. ] doi: 10.17521/cjpe.2004.0067
[9]	王正兴,刘闯,陈文波,等. MODIS增强型植被指数EVI与NDVI初步比较[J].武汉大学学报·信息科学版,2006,31(5):407-410,427. doi: 10.3321/j.issn:1671-8860.2006.05.008
	[ Wang Z X, Liu C, Cheng W B, et al.Preliminary comparison of MODIS-NDVI and MODIS-EVI in Eastern Asia[J]. Geomatics and Information Science of Wuhan University, 2006,31(5):407-410,427. ] doi: 10.3321/j.issn:1671-8860.2006.05.008
[10]	江东,王乃斌,杨小唤,等. NDVI曲线与农作物长势的时序互动规律[J].生态学报,2002,22(2):247-252.
	[ Jiang D, Wang N B, Yang X H, et al.Principles of the interaction between NDVI profile and the growing situation of crops[J]. Acta Ecologica Sinica, 2002,22(2):247-252. ]
[11]	彭文,石军南.面向对象的GEO遥感影像分类与信息提取[J].绿色科技,2011(6):203-206. doi: 10.3969/j.issn.1674-9944.2011.06.089
	[ Peng W, Shi J N.Sensing image classification and information extraction of object-oriented GEO remote[J].Journal of Green Science and Technology, 2011(6):203-206. ] doi: 10.3969/j.issn.1674-9944.2011.06.089
[12]	Balaguer A, Ruiz L A, Hermosilla T, et al.Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented inage classification[J].Computers & Geosciences, 2010(36):231-240
[13]	武维,李玉霞,童玲,等.基于共生矩阵的遥感图像面向对象分割[J].计算机工程与设计,2011,32(2):596-598.
	[ Wu W, Li Y X, Tong L, et al.Object-oriented segmentation of remote sensing image based on co-occurrence matrix[J]. Computer Engineering and Design, 2011,32(2):596-598. ]
[14]	过林. 基于纹理特征的典型遥感影像面状地物提取方法研究[D].郑州:解放军信息工程大学,2011.
	[ Guo L, Research on feature extraction method of typical remote sensing image based on texture features[D]. Zhengzhou: Information Engineering University, 2011. ]
[15]	林晓峰. 基于纹理特征的遥感图像分类算法研究[D].大连:大连理工大学,2007.
	[ Lin X F.Classification algorithms based on texture features for remote sensing image[D]. DaLian: Dalian University of Technology, 2007. ]
[16]	Haralick R.Statistical and structural approaches to texture[J]. Proceeding of the IEEE, 1979,67(5):786-804 doi: 10.1109/PROC.1979.11328
[17]	任国贞,江涛.基于灰度共生矩阵的纹理提取方法研究[J].计算机应用与软件,2014,3111:190-192,325.
	[ Ren G Z, Jiang T.Study on GLCM-based texture extraction methods[J]. Computer Applications and Software, 2014,3111:190-192,325. ]
[18]	李卫国,蒋楠.基于面向对象分类的冬小麦种植面积提取[J].麦类作物学报,2012,32(4):701-705. doi: 10.7606/j.issn.1009-1041.2012.04.018
	[ Li W G, Jiang N.Extraction of winter wheat planting area by object-oriented classification method[J]. Journal of Triticeae Crops, 2012,32(4):701-705. ] doi: 10.7606/j.issn.1009-1041.2012.04.018
[19]	邓乃扬,田英杰.数据挖掘中的新方法–支持向量机[M].北京:科学出版社,2004.
	[ Deng N Y, Tian Y J.New method in data mining[M]. Beijing: Beijing Science Press, 2004. ]
[20]	张学工. 关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
	[ Zhang X G.Introduction to statistical learning theory and support vector machines[J]. Acta Attom Atica Sinica, 2000,26(1):32-42. ]
[21]	李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2):302-304. doi: 10.3969/j.issn.1000-7024.2005.02.008
	[ Li P C, Xu S H.Support vector machine and kernel function characteristic analysis in pattern recognition[J]. Computer Engineering and Design, 2005,26(2):302-304. ] doi: 10.3969/j.issn.1000-7024.2005.02.008
[22]	Baumann M, Ozdogan M, Kuemmerle T, et al.Using the Landsat record to detect forest-cover changes during and after the collapse of the Soviet Union in the temperate zone of European Russia[J]. Remote Sensing of Environment, 2012,124:174-184. doi: 10.1016/j.rse.2012.05.001

作物类型	训练数据			检验数据
作物类型	样方数	样方总面积/km²	面积比/%	样方数	样方总面积/km²	面积比/%
硒砂瓜	100	83.56	39.43	70	53.31	39.47
枸杞	100	69.38	32.74	70	46.95	34.76
大枣	60	58.99	27.83	40	34.82	25.77

地物类型	硒砂瓜	枸杞	大枣	合计
未分类	0	0	0	0
硒砂瓜	39 557	361	0	39 918
枸杞	439	13 190	116	13 745
大枣	0	2986	20 492	23 478
合计	39 996	16 537	20 608	77 141

地物类型	硒砂瓜	枸杞	大枣
制图精度/%	98.90	79.76	99.44
用户精度/%	99.10	95.96	87.28
错分误差/%	0.90	4.04	12.72
漏分精度/%	1.10	20.24	0.56
总体精度/%				94.94
Kappa系数				0.917

类别	光谱单数据源SVM法		光谱结合纹理SVM法		面向对象的SVM法
类别	制图精度/%	用户精度/%	制图精度/%	用户精度/%	制图精度/%	用户精度/%
硒砂瓜	90.02	95.84	92.3	99.58	98.90	99.10
枸杞	76.30	66.72	78.52	72.84	79.76	95.96
大枣	80.78	76.94	91.24	80.74	99.44	87.28
总体精度/%	84.82		89.17		94.94
Kappa系数	0.769		0.815		0.917

面向对象的特色农作物种植遥感调查方法研究

Remote Sensing Investigation Method of Object-oriented Crops with Special Characteristics

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	毛亚萍, 房世峰. 基于机器学习的参考作物蒸散量估算研究[J]. 地球信息科学学报, 2020, 22(8): 1692-1701.
[2]	崔成, 任红艳, 赵璐, 庄大方. 基于街景影像多特征融合的广州市越秀区街道空间品质评估[J]. 地球信息科学学报, 2020, 22(6): 1330-1338.
[3]	杜培军, 王欣, 蒙亚平, 林聪, 张鹏, 卢刚. 面向地理国情监测的变化检测与地表覆盖信息更新方法[J]. 地球信息科学学报, 2020, 22(4): 857-866.
[4]	吴瑞娟, 何秀凤, 王静. 结合像元级与对象级的滨海湿地变化检测方法[J]. 地球信息科学学报, 2020, 22(10): 2078-2087.
[5]	杨浩, 孟娜, 王婧, 郑燕, 赵莉. 基于支持向量机的京津冀城市群热环境时空形态模拟[J]. 地球信息科学学报, 2019, 21(2): 190-200.
[6]	李翔, 朱江, 尹向东, 姚江春, 黄嘉玲, 李密滔. 基于珞珈一号夜间灯光数据的广州市建设用地识别[J]. 地球信息科学学报, 2019, 21(11): 1802-1810.
[7]	黄宗财,仇培元,陆锋,吴升. 基于联合主题特征的网络新闻文本蕴含环境污染事件检测[J]. 地球信息科学学报, 2019, 21(10): 1510-1517.
[8]	李远远, 梅红波, 任晓杰, 胡旭东, 李梦迪. 基于确定性系数和支持向量机的地质灾害易发性评价[J]. 地球信息科学学报, 2018, 20(12): 1699-1709.
[9]	车磊, 王海起, 费涛, 闫滨, 刘玉, 桂丽, 陈冉, 翟文龙. 基于多尺度最小二乘支持向量机优化的克里金插值方法[J]. 地球信息科学学报, 2017, 19(8): 1001-1010.
[10]	罗海峰, 方莉娜, 陈崇成. 车载激光扫描数据路坎点云提取方法[J]. 地球信息科学学报, 2017, 19(7): 861-871.
[11]	周勋, 范泽孟, 岳天祥. 黑河流域植被类型分布模拟分析[J]. 地球信息科学学报, 2017, 19(4): 493-501.
[12]	苏巧梅, 赵尚民, 郭建立. 霍西煤矿区地表滑坡灾害敏感性数值建模与等级划分[J]. 地球信息科学学报, 2017, 19(12): 1613-1622.
[13]	林齐根, 刘燕仪, 刘连友, 王瑛. 支持向量机与Newmark模型结合的地震滑坡易发性评估研究[J]. 地球信息科学学报, 2017, 19(12): 1623-1633.
[14]	彭晨, 余柏蒗, 吴宾, 吴健平. 基于移动激光扫描点云特征图像和SVM的建筑物立面半自动提取方法[J]. 地球信息科学学报, 2016, 18(7): 878-885.
[15]	朱进, 江南, 胡斌. 移动对象多种运动参数在轨迹分类的应用[J]. 地球信息科学学报, 2016, 18(2): 143-150.