Landsat8卫星影像的多子区决策树土地覆被分类方法

李峰; 梁汉东; 米晓楠; 卫爱霞

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Landsat8卫星影像的多子区决策树土地覆被分类方法

李峰, 梁汉东, 米晓楠, 卫爱霞

文章导航 > 红外与激光工程 > 2015 > 44(7): 2224-2230

李峰, 梁汉东, 米晓楠, 卫爱霞. Landsat8卫星影像的多子区决策树土地覆被分类方法[J]. 红外与激光工程, 2015, 44(7): 2224-2230.

引用本文:

李峰, 梁汉东, 米晓楠, 卫爱霞. Landsat8卫星影像的多子区决策树土地覆被分类方法[J]. 红外与激光工程, 2015, 44(7): 2224-2230.

Li Feng, Liang Handong, Mi Xiaonan, Wei Aixia. A multi-subregions decision tree land cover classification approach using Landsat8 image[J]. Infrared and Laser Engineering, 2015, 44(7): 2224-2230.

Citation:

Li Feng, Liang Handong, Mi Xiaonan, Wei Aixia. A multi-subregions decision tree land cover classification approach using Landsat8 image[J]. Infrared and Laser Engineering, 2015, 44(7): 2224-2230.

Landsat8卫星影像的多子区决策树土地覆被分类方法

1.
防灾科技学院防灾工程系,河北三河 065201;
2.
中国矿业大学地球科学与测绘工程学院,北京 100083;
3.
山西气候中心,山西太原 030002

基金项目:

河北省高等学校科学研究计划重点项目(ZD2014203);中央高校基本科研业务费资助项目(ZD2014203);国家自然科学基金(41371449)

详细信息

作者简介:
李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

中图分类号: TP79

A multi-subregions decision tree land cover classification approach using Landsat8 image

1.
Department of Disaster Prevention Engineering,Institute of Disaster Prevention,Sanhe 065201,China;
2.
College of Geoscience and Surveying Engineering,China University of Mining and Technology,Beijing 100083,China;
3.
Shanxi Climate Center,Taiyuan 030002,China

摘要: 乌达矿区的煤火自燃造成了严重的环境、经济和安全灾害, 对该地区的土地覆被变化研究有助于评估煤火灾害的影响程度和范围, 而Landsat8 卫星影像为煤火区的土地覆被分类探测与研究提供了可能。依据乌达地区的地形、地貌和地表辐射特征划分5个子区域, 基于通用单决策树模型, 利用光谱特征分析、高程、坡度和热红外信息对每个子区域分别构建5种不同参数的决策树模型。相比通用单决策树模型以及其他4种普通分类方法, 因减少了土地覆被的混淆度, 多子区决策树模型土地覆被分类的整体精度和Kappa系数更高, 分别达到87.63%和0.86, 尤其是建筑物和煤灰的分类精度有较为明显的提升。
- 土地覆被 /
- 分类 /
- 多子区 /
- 决策树 /
- 煤火
Abstract: Coal fires burning caused serious environmental, economic and safety catastrophe in Wuda district, North China. The land cover change research helped to evaluate the extent of coal fire damage. The image data of Landsat8 satellite offered the possibility of detecting and studying land cover/use in coal fire area. Five subregions were divided from one Wuda image based on topographic, landform and land surface radiation characteristics. Corresponding to each subregion, five different decision tree models with different parameters were respectively constructed based on a general sole decision tree for the whole research area, which was built by spectral characteristics analysis, height, slope and infrared information. By contrasting with a general sole decision tree and other four common classification methods applied to the whole area, land cover accuracy of multi-subregions decision tree classification approach derived higher overall accuracy(87.63%) and Kappa coefficient(0.86) because subregions decreased land-cover confusions. In particular, the accuracy of building and coal ash classification mapping showed a marked increase.
- land cover /
- classification /
- multi-subregions /
- decision tree /
- coal fire

[1]	Kuenzer C, Zhang J, Sun Y, et al. Coal fires revisited: the Wuda coal field in the aftermath of extensive coal fire research and accelerating extinction activities[J]. International Journal of Coal Geology, 2012, 102: 75-86.
[2]
[3]	Prakash A, Gupta R P. Land-use mapping and change detection in a coal mining area-a case study in the Jharia coalfield, India[J]. International Journal of Remote Sensing, 1998, 19(3): 391-410.
[4]
[5]
[6]	Gao Y, Mas J F, Maathuis B H P, et al. Comparison of pixel-based and object-oriented image classification approaches-a case study in a coal fire area[J]. International Journal of Remote Sensing, 2006, 27(18): 4039-4055.
[7]
[8]	Zhang C, Guo S, Guan Y, et al. The approaches of land cover classification of the Wuda coal fire area[J]. Journal of Remote Sensing, 2011, 15(1): 148-161. (in Chinese)
[9]
[10]	Zhou Q, Robson M. Contextual information is ultimately necessary if one is to obtain accurate image classifications[J]. International Journal of Remote Sensing, 2001, 22:3457-3470.
[11]
[12]	Prol-Ledesma R M, Uribe-Alcantara E M, Diaz M O. Use of cartographic data and Landsat TM images to determine land use change in the vicinity of Mexico City [J]. International Journal of Remote Sensing, 2002, 23(9): 1927-1933.
[13]	Blaschke T, Strobl J. What's wrong with pixels? Some recent development interfacing remote sensing and GIS[J]. GeoBIT/GIS, 2001, 6: 12-17.
[14]
[15]	Song X F, Duan Z, Jiang X G. Comparision of aritificial neural networks and support vector machine classifiers for land cover classification in northern China using a SPOT-5 HRG image[J]. International Journal of Remote Sensing, 2012, 33(10): 3301-3320.
[16]
[17]
[18]	Rowan L C, Mars J C. Lithologic Mapping in the Mountain Pass, California area using advanced spaceborne thermal emission and reflection radiometer(ASTER) data [J]. Remote Sensing of Enviroment, 2003, 84: 350-366.
[19]	Wang K, Qi H P. Researching on the assorting methods of land utility and overburden remote sense[J]. Xi'an University of Architecture, 2008, 34(5): 353-354. (in Chinese)

[1]	廖辉传, 赵海霞. 基于分类器决策融合的红外图像目标识别方法 . 红外与激光工程, 2022, 51(8): 20210725-1-20210725-6. doi: 10.3788/IRLA20210725
[2]	邵慧, 撒贝宁, 李伟, 陈育伟, 刘璐, 陈杰, 孙龙, 胡玉霞. 一种适用于古建筑建模的全波形高光谱激光雷达设计与实现 . 红外与激光工程, 2022, 51(8): 20210786-1-20210786-10. doi: 10.3788/IRLA20210786
[3]	王雷光, 耿若筝, 代沁伶, 王军, 郑晨, 付志涛. 高光谱-LiDAR 融合的条件随机场分类方法 . 红外与激光工程, 2021, 50(12): 20210112-1-20210112-12. doi: 10.3788/IRLA20210112
[4]	He Zixin, Shao Hui, Guo Hang, Chen Jie. Classification of coal/rock based on Hyperspectral LiDAR calibration-free signals . 红外与激光工程, 2021, 50(10): 20200518-1-20200518-9. doi: 10.3788/IRLA20200518
[5]	盛家川, 陈雅琦, 王君, 韩亚洪. 深度学习结构优化的图像情感分类 . 红外与激光工程, 2020, 49(11): 20200269-1-20200269-10. doi: 10.3788/IRLA20200269
[6]	卢瑞涛, 任世杰, 申璐榕, 杨小冈. 基于稀疏表示多子模板的鲁棒目标跟踪算法 . 红外与激光工程, 2019, 48(3): 326003-0326003(8). doi: 10.3788/IRLA201948.0326003
[7]	解格飒, 王红军, 王大森, 田爱玲, 刘丙才, 朱学亮, 刘卫国. 超光滑表面缺陷的分类检测研究 . 红外与激光工程, 2019, 48(11): 1113003-1113003(7). doi: 10.3788/IRLA201948.1113003
[8]	张昀普, 徐公国, 单甘霖, 段修生. 移动式雷达/红外辐射控制的调度方法 . 红外与激光工程, 2019, 48(9): 904004-0904004(8). doi: 10.3788/IRLA201948.0904004
[9]	胡善江, 贺岩, 陶邦一, 俞家勇, 陈卫标. 基于深度学习的机载激光海洋测深海陆波形分类 . 红外与激光工程, 2019, 48(11): 1113004-1113004(8). doi: 10.3788/IRLA201948.1113004
[10]	张东阁, 傅雨田. 基于一类支持向量机的盲元检测方法 . 红外与激光工程, 2018, 47(4): 404001-0404001(7). doi: 10.3788/IRLA201847.0404001
[11]	马跃, 张文豪, 张智宇, 马昕, 李松. 基于半解析模型的激光测高回波海水海冰波形分类方法 . 红外与激光工程, 2018, 47(5): 506005-0506005(7). doi: 10.3788/IRLA201847.0506005
[12]	侯榜焕, 姚敏立, 贾维敏, 沈晓卫, 金伟. 空谱结构保持的高光谱图像分类 . 红外与激光工程, 2017, 46(12): 1228001-1228001(8). doi: 10.3788/IRLA201746.1228001
[13]	杨新锋, 胡旭诺, 粘永健. 基于分类的高光谱图像压缩算法 . 红外与激光工程, 2016, 45(2): 228003-0228003(4). doi: 10.3788/IRLA201645.0228003
[14]	张迪飞, 张金锁, 姚克明, 成明伟, 吴永国. 基于SVM分类的红外舰船目标识别 . 红外与激光工程, 2016, 45(1): 104004-0104004(6). doi: 10.3788/IRLA201645.0104004
[15]	刘志青, 李鹏程, 郭海涛, 张保明, 陈小卫, 丁磊, 赵传. 基于相关向量机的机械LiDAR点云数据分类 . 红外与激光工程, 2016, 45(S1): 98-104. doi: 10.3788/IRLA201645.S130006
[16]	张采芳, 田岩, 李江. 基于几何特征分析的路面裂缝分类算法研究 . 红外与激光工程, 2015, 44(4): 1359-1364.
[17]	张东彦, 赵晋陵, 黄林生, 马雯萩. 用于高光谱图像分类的归一化光谱指数的构建与应用 . 红外与激光工程, 2014, 43(2): 586-594.
[18]	普晗晔, 王斌, 张立明. 基于流形学习的新高光谱图像降维算法 . 红外与激光工程, 2014, 43(1): 232-237.
[19]	秦玉华, 丁香乾, 宫会丽. 高维特征选择方法在近红外光谱分类中的应用 . 红外与激光工程, 2013, 42(5): 1355-1359.
[20]	丁玲, 唐娉, 李宏益. 基于ISOMAP的高光谱遥感数据的降维与分类 . 红外与激光工程, 2013, 42(10): 2707-2711.

点击查看大图

计量

文章访问数: 365
HTML全文浏览量: 49
PDF下载量: 393
被引次数: 0

Landsat8卫星影像的多子区决策树土地覆被分类方法

1. 防灾科技学院防灾工程系,河北三河 065201;

2. 中国矿业大学地球科学与测绘工程学院,北京 100083;

3. 山西气候中心,山西太原 030002

作者简介:
李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

收稿日期: 2014-11-05
修回日期: 2014-12-10
刊出日期: 2015-07-25

基金项目:

河北省高等学校科学研究计划重点项目(ZD2014203);中央高校基本科研业务费资助项目(ZD2014203);国家自然科学基金(41371449)

中图分类号: TP79

关键词:

摘要: 乌达矿区的煤火自燃造成了严重的环境、经济和安全灾害, 对该地区的土地覆被变化研究有助于评估煤火灾害的影响程度和范围, 而Landsat8 卫星影像为煤火区的土地覆被分类探测与研究提供了可能。依据乌达地区的地形、地貌和地表辐射特征划分5个子区域, 基于通用单决策树模型, 利用光谱特征分析、高程、坡度和热红外信息对每个子区域分别构建5种不同参数的决策树模型。相比通用单决策树模型以及其他4种普通分类方法, 因减少了土地覆被的混淆度, 多子区决策树模型土地覆被分类的整体精度和Kappa系数更高, 分别达到87.63%和0.86, 尤其是建筑物和煤灰的分类精度有较为明显的提升。

English Abstract

A multi-subregions decision tree land cover classification approach using Landsat8 image

1. Department of Disaster Prevention Engineering,Institute of Disaster Prevention,Sanhe 065201,China;

2. College of Geoscience and Surveying Engineering,China University of Mining and Technology,Beijing 100083,China;

3. Shanxi Climate Center,Taiyuan 030002,China

Received Date: 2014-11-05
Rev Recd Date: 2014-12-10
Publish Date: 2015-07-25

Keywords:

Abstract: Coal fires burning caused serious environmental, economic and safety catastrophe in Wuda district, North China. The land cover change research helped to evaluate the extent of coal fire damage. The image data of Landsat8 satellite offered the possibility of detecting and studying land cover/use in coal fire area. Five subregions were divided from one Wuda image based on topographic, landform and land surface radiation characteristics. Corresponding to each subregion, five different decision tree models with different parameters were respectively constructed based on a general sole decision tree for the whole research area, which was built by spectral characteristics analysis, height, slope and infrared information. By contrasting with a general sole decision tree and other four common classification methods applied to the whole area, land cover accuracy of multi-subregions decision tree classification approach derived higher overall accuracy(87.63%) and Kappa coefficient(0.86) because subregions decreased land-cover confusions. In particular, the accuracy of building and coal ash classification mapping showed a marked increase.

全文HTML

参考文献 (19)

下载: 全尺寸图片幻灯片

返回文章

用微信扫码二维码

分享至好友和朋友圈

留言板

Landsat8卫星影像的多子区决策树土地覆被分类方法

作者简介: 李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

A multi-subregions decision tree land cover classification approach using Landsat8 image

计量

出版历程

Landsat8卫星影像的多子区决策树土地覆被分类方法

1. 防灾科技学院 防灾工程系,河北 三河 065201; 2. 中国矿业大学 地球科学与测绘工程学院,北京 100083; 3. 山西气候中心,山西 太原 030002

作者简介: 李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

English Abstract

A multi-subregions decision tree land cover classification approach using Landsat8 image

1. Department of Disaster Prevention Engineering,Institute of Disaster Prevention,Sanhe 065201,China; 2. College of Geoscience and Surveying Engineering,China University of Mining and Technology,Beijing 100083,China; 3. Shanxi Climate Center,Taiyuan 030002,China

全文HTML

目录

作者简介:
李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

1. 防灾科技学院防灾工程系,河北三河 065201;

2. 中国矿业大学地球科学与测绘工程学院,北京 100083;

3. 山西气候中心,山西太原 030002

作者简介:
李峰(1979-),男,讲师,博士,主要从事遥感、车载/机载LiDAR点云处理方面的研究。Email:lif1223@aliyun.com

1. Department of Disaster Prevention Engineering,Institute of Disaster Prevention,Sanhe 065201,China;

2. College of Geoscience and Surveying Engineering,China University of Mining and Technology,Beijing 100083,China;

3. Shanxi Climate Center,Taiyuan 030002,China