基于多纹理和支持向量机的ZY-102C星HR数据分类

李粉玲; 常庆瑞; 刘佳岐; 刘京

doi:10.13203/j.whugis20140356

基于多纹理和支持向量机的ZY-102C星HR数据分类

doi: 10.13203/j.whugis20140356

李粉玲^1,2,
常庆瑞^1,2,,
刘佳岐¹,
刘京^1,2

1.
西北农林科技大学资源环境学院, 陕西杨凌, 712100;
2.
农业部西北植物营养与农业环境重点实验室, 陕西杨凌, 712100

基金项目: 国家863计划(2013AA102401);国家教育部博士点专项基金(20120204110013)。

详细信息

作者简介:
李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

通讯作者: 常庆瑞,博士,教授,博士生导师。changqr@nwsuaf.edu.cn

中图分类号: TP79

SVM Classification with Multi-texture Data of ZY-102C HR Image

LI Fenling^1,2,
CHANG Qingrui^{1,2
,},
LIU Jiaqi¹,
LIU Jing^1,2

1.
College of Natural Resources and Environment, Northwest A & F University, Yangling 712100, China;
2.
Key Laboratory of Plant Nutrition and the Agri-Environment in Northwest China, Ministry of Agriculture, Yangling 712100, China

Funds: The National High Technology Research and Development Program of China(863 Program), No.2013AA102401; The PhD Programs Foundation of Ministry of Education of China, No.20120204110013.

摘要: 基于国产资源一号02C星高分辨率(high resolution,HR)影像,提取了基于变差函数、灰度共生矩阵和梯度的多纹理特征,结合光谱信息构建了基于支持向量机(support vector machine,SVM)的多源信息复合模型的图像分类方法,并与传统最大似然法和决策树法的分类结果进行了比较。研究表明,变差函数纹理和梯度纹理参与的多源复合数据有效提高了图像的分类精度,总分类精度由85.14%提高到87.43%,Kappa系数由0.82提高到0.85;绝对值变差函数为纹理最佳窗口分析提供了理论依据,基于累积步长提取的纹理特征能显著提升图像分类的精度,分类准确率提高了13.94%,Kappa系数增加了0.17;基于多源复合数据的SVM高空间分辨率遥感图像分类方法能有效解决传统图像分类结果破碎的问题,比最大似然方法和决策树法的分类精度显著提高,总精度达到89.14%,Kappa系数为0.87,分别提高了6.85%和10.84%。实验表明,ZY-102C星HR数据在冬小麦信息提取中具有一定的稳定性和优势。
- 高分辨率相机 /
- 多纹理特征 /
- 累积步长 /
- 支持向量机 /
- 精准农业
Abstract: Based on a ZY-102C HR Image, three kinds of textures, the variogram texture, gray level co-occurrence matrix texture, and gradient texture, were extracted. Then, we present a new SVM classification method with multi-source data by integrating the spectral information and these three different textures. The classification result was compared with results using Maximum Likelihood Classification(MLC) and Decision Tree(DT) method. The study shows that:(1) Variogram texture and gradient texture involved in multi-source data can effectively improve image classification precision with an overall accuracy from 85.14% to 87.43% and Kappa coefficient from 0.82 to 0.85;(2) The variation function of absolute value form provides a theoretical basis for the optimal texture window analysis, and textural features based on the average step can significantly improve classification accuracy with an overall accuracy from 75.2% to 87.14% and Kappa coefficient from 0.7 to 0.87;(3) Based on multi-source data, the SVM classification method for high spatial resolution remote sensing images can effectively overcome the fragmentation problems associated with traditional image classification methods. Our results were significantly superior to MLC and DT with an overall accuracy of 89.14% and Kappa coefficient of 0.87;(4) The resource satellite data ZY-10C has a certain stability and advantages for the extraction of winter wheat.
- high resolution camera(HR camera) /
- multi-textural feature /
- accumulative lag distance /
- support vector machine(SVM) /
- precision agriculture

[1]	Shu Ning. On the Texture of Multi-spectral and Super-dimensional Images[J]. Geomatics and Information Science of Wuhan University, 2004,29(4):292-295(舒宁.关于多光谱和高光谱影像的纹理问题[J].武汉大学学报·信息科学版,2004,29(4):292-295)
[2]	Yu Q, Gong P, Clinton N,et al. Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery[J]. Photogrammetric Engineering and Remote Sensing, 2006,72(7):799-811
[3]	Shackelford A K, Davis C H. A Combined Fuzzy Pixel-based and Object-based Approach for Classification of High-resolution Multispectral Data over Urban Areas[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2003,41(10):2354-2363
[4]	Zhang Qian, Huang Xin, Zhang Liangpei. Multiscale Image Segmentation and Classification with Supervised ECHO of High Spatial Resolution Remotely Sensed Imagery[J]. Geomatics and Information Science of Wuhan University, 2011, 36(1):117-121(张倩, 黄昕, 张良培. 多尺度同质区域提取的高分辨率遥感影像分类研究[J]. 武汉大学学报·信息科学版, 2011, 36(1):117-121)
[5]	Yang Bo, Wang Mi. On-orbit Geometric Calibration Method of ZY-102C Panchromatic Camera[J]. Journal of Remote Sensing, 2013,17(5):1175-1190
[6]	Liu Gang, Xu Hongjiang, Ma Haitao, et al. Land Use Change Information Extraction Methods and Application of Land Resources High Resolution System Based on Resource 02C Satellite[J].Geomatics and Spatial Information Technology, 2013,36(4):65-68(刘刚,许宏健,马海涛,等.基于资源一号02C卫星数据的土地资源高分系统变化信息提取方法应用研究[J].测绘与空间地理信息,2013,36(4):65-68)
[7]	Wen Xiongfei, Chen Beiqing, Shen Shaohong, et al. Image Qualitu Evaluation for ZY-002C Satellite P/MS Sensor and the Potential of Its Application in Water Conservancy[J]. Journal of Yangtze River Scientific Research Institue, 2012,29(10):118-121(文雄飞,陈蓓青,申邵洪,等.资源一号02C卫星P/MS传感器数据质量评价及其在水利行业中的应用潜力分析[J].长江科学院院报,2012,29(10):118-121)
[8]	Moran E F. Land Cover Classification in a Complex Urban-rural Landscape with Quickbird Imagery[J]. Photogrammetric Engineering and Remote Sensing, 2010,76(10):1159-1168
[9]	James R C. Spectral and Texture Classification of Single and Multiple Band Digital Images[J]. Computers and Geosciences, 1996,22(8):849-865
[10]	Su W, Li J, Chen Y, et al. Textural and Local Spatial Statistics for the Object Oriented Classification of Urban Areas Using High Resolution Imagery[J]. International Journal of Remote Sensing, 2008,29(11):3105-3117
[11]	Tao Yang.Texture Analysis Based Research on Terrain Morphology Characteristies[D]. Nanjing:Nanjing Normal University, 2011(陶旸. 基于纹理分析方法的DEM地形特征研究[D]. 南京:南京师范大学,2011)
[12]	Hu Wenying, Jiao Yuanmei. The Study Process of Texture Feature Extraction for Remote Sensing Image[J]. Yunnan Geographic Environment Research, 2007,19(3):66-71,76(胡文英,角媛梅.遥感图像纹理信息提取方法综述[J].云南地理环境研究,2007,19(3):66-71,76)
[13]	Li Peijun, Li Zhengxiao. Comparison of Three Geostatistical Texture Measures for Remotely Sensed Data Classification[J]. Geography and Geo-Information Science, 2003,19(4):89-92(李培军,李争晓. 三种地统计学图像纹理用于遥感图像分类的比较[J].地理与地理信息科学,2003,19(4):89-92)
[14]	Chica-Olmo M, Arbarca-Hernandez F. ComputingGeostatistical Image Texture for Remotely Sensed Data Classification[J]. Computers and Geosciences, 2000,26(4):373-383
[15]	Zhang Jinshui, He Chunyang, Pan Yaozhong, et al. The High Spatial Resolution RS Image Classification Based on SVM Method with the Multi-source Data[J].Journal of Remote Sensing, 2006,10(1):49-57(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].遥感学报, 2006,10(1):49-57)
[16]	Wu Zhaocong, Ouyang Qundong, Hu Zhongwen. Polarimetric SAR Image Classification Using Watershed Transformation and Support Vector Machine[J]. Geomatics and Information Science of Wuhan University, 2012, 37(1):7-10(巫兆聪, 欧阳群东, 胡忠文. 应用分水岭变换与支持向量机的极化SAR图像分类[J]. 武汉大学学报·信息科学版, 2012, 37(1):7-10)
[17]	Melgani F, Bruzzone L. Classification of Hyperspectral Remote Sensing Images with Support Vector Machines[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2004, 42(8):1778-1790
[18]	Huang C, Davis L S, Townshend J R G. An Assessment of Support Vector Machines for Land Cover Classification[J]. International Journal of Remote Sensing, 2002,23(4):725-749
[19]	Curran P J. The Semivariogram in Remote Sensing:An Introduction[J]. Remote Sensing of Environment, 1988,24(3):493-507
[20]	Wu S, Xu B, Wang L. Urban Land-use Classification Using Variogram-based Analysis with an Aerial Photograph[J]. Photogrammetric Engineering and Remote Sensing, 2006,72(7):813-822
[21]	Dell'Acqua F, Gamba P, Trianni G. Semi-automatic Choice of Scale-dependent Features for Satellite SAR Image Classification[J]. Pattern Recognition Letters, 2006, 27(4):244-251
[22]	Li Xiaotao,Pan Shibing,Song Xiaoning. Remote Sensing Image Classification Method Based on Geostatistics Texture[J]. Geography and Geo-Information Science, 2009,25(2):30-33(李小涛,潘世兵,宋小宁.基于地质统计学纹理特征的遥感影像分类方法研究[J].地理与地理信息科学,2009,25(2):30-33)
[23]	Soh L K, Tsatsoulis C. Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-occurrence Matrices[J]. IEEE Transactions on Geoscience and Remote Sensing,1999,37(2):780-795
[24]	Srinivasan G N, Shobha G. Statistical Texture Analysis[J]. Proceedings of World Academy of Science, Engineering and Technology, 2008, 36:1264-1269
[25]	He Chunyang, Cao Xin, Shi Peijun, et al. Incorporation of Texture and Structure Information for Urban Building Detection by Using Landsat 7 ETM+ Panchromatic Image[J]. Geomatics and Information Science of Wuhan University, 2004, 29(9):800-804(何春阳, 曹鑫, 史培军, 等. 基于Landsat7 ETM+全色数据纹理和结构信息复合的城市建筑信息提取[J]. 武汉大学学报·信息科学版, 2004, 29(9):800-804)
[26]	Zhou W, Troy A, Grove M. Object-based Land Cover Classification and Change Analysis in the Baltimore Metropolitan Area Using Multitemporal High Resolution Remote Sensing Data[J]. Sensors, 2008, 8(3):1613-1636
[27]	Chang C C, Lin C J. LIBSVM:a Library for Support Vector Machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(27):1-27
[28]	Congalton R G. A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data[J]. Remote Sensing of Environment, 1991,37(1):35-46

[1]	刘雅婷, 龚龑, 段博, 方圣辉, 彭漪. 多时相NDVI与丰度综合分析的油菜无人机遥感长势监测 . 武汉大学学报 ( 信息科学版), 2020, 45(2): 265-272. doi: 10.13203/j.whugis20180161
[2]	徐胜华, 刘纪平, 王想红, 张玉, 林荣福, 张蒙, 刘猛猛, 姜涛. 熵指数融入支持向量机的滑坡灾害易发性评价方法—以陕西省为例 . 武汉大学学报 ( 信息科学版), 2020, 45(8): 1214-1222. doi: 10.13203/j.whugis20200109
[3]	段佩祥, 钱海忠, 何海威, 谢丽敏, 罗登瀚. 基于支持向量机的线化简方法 . 武汉大学学报 ( 信息科学版), 2020, 45(5): 744-752, 783. doi: 10.13203/j.whugis20180434
[4]	祝胜男, 郭炜炜, 柳彬, 张增辉, 郁文贤. 利用超像素级上下文特征进行靠岸集装箱船检测 . 武汉大学学报 ( 信息科学版), 2019, 44(4): 578-585. doi: 10.13203/j.whugis20170129
[5]	鲍蕊, 薛朝辉, 张像源, 苏红军, 杜培军. 综合聚类和上下文特征的高光谱影像分类 . 武汉大学学报 ( 信息科学版), 2017, 42(7): 890-896. doi: 10.13203/j.whugis20150043
[6]	刘操, 郑宏, 黎曦, 余典. 基于多通道融合HOG特征的全天候运动车辆检测方法 . 武汉大学学报 ( 信息科学版), 2015, 40(8): 1048-1053. doi: 10.13203/j.whugis20130341
[7]	王凯, 舒宁, 孔祥兵, 李亮. 一种多特征转换的高光谱影像自适应分类方法 . 武汉大学学报 ( 信息科学版), 2015, 40(5): 612-616. doi: 10.13203/j.whugis20130384
[8]	彭令, 牛瑞卿, 赵艳南, 邓清禄. 基于核主成分分析和粒子群优化支持向量机的滑坡位移预测 . 武汉大学学报 ( 信息科学版), 2013, 38(2): 148-152,161.
[9]	武雪玲, 任福, 牛瑞卿, 彭令. 斜坡单元支持下的滑坡易发性评价支持向量机模型 . 武汉大学学报 ( 信息科学版), 2013, 38(12): 1499-1503.
[10]	巫兆聪, 欧阳群东, 胡忠文. 应用分水岭变换与支持向量机的极化SAR图像分类 . 武汉大学学报 ( 信息科学版), 2012, 37(1): 7-10.
[11]	王忠武, 刘顺喜, 陈晓东. IKONOS图像融合中自动拟合低分辨率全色图像的方法 . 武汉大学学报 ( 信息科学版), 2010, 35(11): 1283-1287.
[12]	杨柳, 刘艳芳. 将微粒群和支持向量机用于耕地驱动因子选择的研究 . 武汉大学学报 ( 信息科学版), 2010, 35(2): 248-251.
[13]	熊华, 刘耀林, 车珊珊, 张俊峰. 基于支持向量机的土地利用变化模拟模型 . 武汉大学学报 ( 信息科学版), 2009, 34(3): 366-369.
[14]	范千, 花向红. 基于相空间重构与支持向量机预测滑坡位移的一种新方法 . 武汉大学学报 ( 信息科学版), 2009, 34(2): 248-251.
[15]	王新洲, 范千, 许承权, 李昭. 基于小波变换和支持向量机的大坝变形预测 . 武汉大学学报 ( 信息科学版), 2008, 33(5): 469-471.
[16]	陈刚, 鄂栋臣. 基于纹理分析和支持向量机的极地冰雪覆盖区的云层检测 . 武汉大学学报 ( 信息科学版), 2006, 31(5): 403-406.
[17]	徐芳, 梅文胜, 燕琴. 支持向量机中遗传模糊C-均值的样本预选取方法 . 武汉大学学报 ( 信息科学版), 2005, 30(10): 921-924.
[18]	梅建新, 段汕, 秦前清. 基于支持向量机的特定目标检测方法 . 武汉大学学报 ( 信息科学版), 2004, 29(10): 912-915,932.
[19]	沙宗尧, 边馥苓. 远程智能诊断与决策支持系统的设计与开发 . 武汉大学学报 ( 信息科学版), 2004, 29(12): 1055-1058.
[20]	徐芳, 燕琴. 基于支持向量机的航空影像纹理分类研究 . 武汉大学学报 ( 信息科学版), 2003, 28(5): 517-520.

点击查看大图

计量

文章访问数: 2834
HTML全文浏览量: 78
PDF下载量: 378
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于多纹理和支持向量机的ZY-102C星HR数据分类

doi: 10.13203/j.whugis20140356

作者简介:
李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

通讯作者: 常庆瑞,博士,教授,博士生导师。changqr@nwsuaf.edu.cn

SVM Classification with Multi-texture Data of ZY-102C HR Image

计量

基于多纹理和支持向量机的ZY-102C星HR数据分类

doi: 10.13203/j.whugis20140356

1. 西北农林科技大学资源环境学院, 陕西杨凌, 712100;

2. 农业部西北植物营养与农业环境重点实验室, 陕西杨凌, 712100

作者简介:
李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

通讯作者: 常庆瑞,博士,教授,博士生导师。changqr@nwsuaf.edu.cn

English Abstract

SVM Classification with Multi-texture Data of ZY-102C HR Image

1. College of Natural Resources and Environment, Northwest A & F University, Yangling 712100, China;

2. Key Laboratory of Plant Nutrition and the Agri-Environment in Northwest China, Ministry of Agriculture, Yangling 712100, China

全文HTML

目录

留言板

基于多纹理和支持向量机的ZY-102C星HR数据分类

doi: 10.13203/j.whugis20140356

作者简介: 李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

通讯作者: 常庆瑞,博士,教授,博士生导师。changqr@nwsuaf.edu.cn

SVM Classification with Multi-texture Data of ZY-102C HR Image

计量

出版历程

基于多纹理和支持向量机的ZY-102C星HR数据分类

doi: 10.13203/j.whugis20140356

1. 西北农林科技大学资源环境学院, 陕西 杨凌, 712100; 2. 农业部西北植物营养与农业环境重点实验室, 陕西 杨凌, 712100

作者简介: 李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

通讯作者: 常庆瑞,博士,教授,博士生导师。changqr@nwsuaf.edu.cn

English Abstract

SVM Classification with Multi-texture Data of ZY-102C HR Image

1. College of Natural Resources and Environment, Northwest A & F University, Yangling 712100, China; 2. Key Laboratory of Plant Nutrition and the Agri-Environment in Northwest China, Ministry of Agriculture, Yangling 712100, China

全文HTML

目录

作者简介:
李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

1. 西北农林科技大学资源环境学院, 陕西杨凌, 712100;

2. 农业部西北植物营养与农业环境重点实验室, 陕西杨凌, 712100

作者简介:
李粉玲,博士生,主要从事土地资源与空间信息技术研究。fenlingli@163.com

1. College of Natural Resources and Environment, Northwest A & F University, Yangling 712100, China;

2. Key Laboratory of Plant Nutrition and the Agri-Environment in Northwest China, Ministry of Agriculture, Yangling 712100, China