基于多源多时相遥感影像的山地森林分类决策树模型研究

doi:10.11873/j.issn.1004-0323.2016.1.0031

遥感技术与应用

2016, Vol. 31

Issue (1): 31-41 DOI: 10.11873/j.issn.1004-0323.2016.1.0031

山地遥感专栏

基于多源多时相遥感影像的山地森林分类决策树模型研究

雷光斌^1,2,李爱农¹,谭剑波^1,2,张正健¹,边金虎^1,2,靳华安¹,赵伟¹,曹小敏^1,2

(1.中国科学院水利部成都山地灾害与环境研究所,四川成都610041；
2中国科学院大学,北京100049)

Forest Types Mapping in Mountainous Area Using Multi\|source and Multi-temporal Satellite Images and Decision Tree Models

Lei Guangbin^1,2,Li Ainong¹,Tan Jianbo^1,2,Zhang Zhengjian¹,Bian Jinhu^1,2,Jin Huaan¹,Zhao Wei¹,Cao Xiaomin^1,2

(1.Institute of Mountain Hazards and Environment,Chinese Academy of Sciences,Chengdu 610041,China;2.University of Chinese Academy of Sciences,Beijing 100049,China)

全文: PDF(7342 KB)

摘要：

山地是森林重要的分布区,然而山地多样的森林类型、高度异质化的景观格局、突出的地形效应以及云、雾的干扰均不同程度地影响了山地森林类型的遥感自动制图。多源多时相遥感影像提供的季相节律信息是当前提高土地覆被遥感制图精度的重要信息源之一。以岷江上游地区为研究区,以国产环境减灾卫星多光谱CCD(简称HJ CCD)影像和美国Landsat TM影像为数据源,以决策树为分类方法,根据参与分类影像的时相差异设计了5组对比实验(生长季单时相组、非生长季单时相组、生长季多时相组、非生长季多时相组、全时相组),对比论证多源多时相遥感影像对山地森林类型自动制图的贡献和作用。对比结果表明:生长季和非生长季相结合的多时相遥感影像较单时相或单一类型(生长季或非生长季)多时相遥感影像,更能显著提高山地森林类型自动制图精度,且能降低分类决策树的复杂程度,更有利于山地森林类型的自动提取。

关键词： 山地森林制图; 多源多时相影像; 决策树模型; 面向对象

Abstract:

Mountain is the major distribution areas of forest.However,the accuracy of forest types mapping in this region by remote sensing technology is affected by various factors directly or indirectly,such as heterogeneous landscape patterns,conspicuous topographic effects and frequent cloud containmination of satellite images.Temporal signature contained in the multi\|source and multi\|temporal satellite images is one of the important information to improve the accuracy of land cover product.A case study was conducted at the upper reaches of Minjiang River,and the native HJ CCD images and Landsat TM images were taken as main input data.Five controlled experiments with different satellite images (single growing season satellite images,single non\|growing season satellite images,multiple growing season satellite images,multiple non\|growing season satellite and all\|temporal satellite images) were designed to validate the contribution of multi\|source and multi\|temporal infomation for automatically mapping of forest types in moutainous area.Comparsion result shows that the multi\|temporal information combined with growing season and non\|growing season can significantly improve the mapping accuracy of forest types in mountainous area compared with single\|temporal or multi\|temporal images of single season,and can simplify the classification rule sets.

Key words: Forest types mapping in mountainous area Multi-source and multi-temporal remote sensing images Decision tree Object-oriented classification

收稿日期: 2015-12-10 出版日期: 2016-04-05

TP 75

基金资助:

国家自然科学基金项目（41271433,41571373），中国科学院战略性先导科技专项子课题（XDA05050105）和中国科学院“百人计划”项目联合资助。

通讯作者: 李爱农(1974-)，男，安徽庐江人，研究员，中国科学院“百人计划”、四川省“千人计划”入选者，主要从事山地定量遥感及其应用研究。Email:ainongli@imde.ac.cn。

作者简介: 雷光斌(1987-)，男，四川广元人，博士研究生，主要从事山地土地覆被遥感监测与模拟研究。Email:leiguangbin@imde.ac.cn。

	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
	雷光斌
	李爱农
	谭剑波
	张正健
	边金虎
	靳华安
	赵伟
	曹小敏

引用本文:

雷光斌,李爱农,谭剑波,张正健,边金虎,靳华安,赵伟,曹小敏. 基于多源多时相遥感影像的山地森林分类决策树模型研究[J]. 遥感技术与应用, 2016, 31(1): 31-41.

Lei Guangbin,Li Ainong,Tan Jianbo,Zhang Zhengjian,Bian Jinhu,Jin Huaan,Zhao Wei,Cao Xiaomin. Forest Types Mapping in Mountainous Area Using Multi\|source and Multi-temporal Satellite Images and Decision Tree Models. Remote Sensing Technology and Application, 2016, 31(1): 31-41.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2016.1.0031 或 http://www.rsta.ac.cn/CN/Y2016/V31/I1/31

［1］Klenner W,Arsenault A,Brockerhoff E G,et al.Biodiversity in Forest Ecosystems and Landscapes:A Conference to Discuss Future Directions in Biodiversity Management for Sustainable Forestry［J］.Forest Ecology and Management,2009,258:1-4.

［2］Dixon R K,Brown S,Houghton R A,et al.Carbon Pools and Flux of Global Forest Ecosystems［J］.Science,1994,263(5144):185-190.

［3］Hansen M C,Potapov P V,Moore R,et al.High-resolution Global Maps of 21st-Century Forest Cover Change［J］.Science,2013,342(6160):850-853.

［4］Chen X G,Zhang X Q,Zhang Y P,et al.Carbon Sequestration Potential of the Stands Under the Grain for Green Program in Yunnan Province,China［J］.Forest Ecology and Management,2009,258(3):199-206.

［5］Lei Guangbin,Li Ainong,Bian Jinhu,et al.An Practical Method for Automatically Identifying the Evergreen and Deciduous Characteristic of Forests at Mountainous Areas:A Case Study in Mt.Gongga Region［J］.Acta Ecologica Sinica,2014,34(24):7210-7221.［雷光斌,李爱农,边金虎,等.基于阈值法的山区森林常绿、落叶特征遥感自动识别方法研究——以贡嘎山地区为例［J］.生态学报,2014,34(24):7210-7221.］

［6］Hou Z,Xu Q,Nuutinen T,et al.Extraction of Remote Sensing-based Forest Management Units in Tropical Forests［J］.Remote Sensing of Environment,2013,130:1-10.

［7］Heenkenda M K,Joyce K E,Maier S W,et al.Mangrove Species Identification:Comparing WorldView-2 with Aerial Photographs［J］.Remote Sensing,2014,6(7):6064-6088.［8］Li A N,Jiang J G,Bian J H,et al.Combining the Matter Element Model with the Associated Function of Probability Transformation for Multi-source Remote Sensing Data Classification in Mountainous Regions［J］.ISPRS Journal of Photogrammetry and Remote Sensing,2012,67:80-92.

［9］Zhang Huanxue,Cao Xin,Li Qiangzi,et al.Research on Crop Identification Using Multi-temporal NDVI HJ Images［J］.Remote Sensing Technology and Application,2015,30(2):304-311.［张焕雪,曹新,李强子,等.基于多时相环境星NDVI时间序列的农作物分类研究［J］.遥感技术与应用,2015,30(2):304-311.］

［10］Wulder M A,Masek J G,Cohen W B,et al.Opening the Archive:How Free Data has Enabled the Science and Monitoring Promise of Landsat［J］.Remote Sensing of Environment,2012,122:2-10.

［11］Bian J H,Li A N,Jin H A,et al.Auto-registration and Orthorecification Algorithm for the Time Series HJ-1A/B CCD Images［J］.Journal of Mountain Science,2013,10(5):754-767.

［12］Li Ainong,Jiang Jingang,Bian Jinhu,et al.Experiment and Accuracy Analysis of Automated Registration and Orthorectification for Landsat-like Images based on AROP［J］.Remote Sensing Technology and Application,2012,27(1):23-32.［李爱农,蒋锦刚,边金虎,等.基于AROP程序包的类Landsat遥感影像配准与正射纠正试验和精度分析［J］.遥感技术与应用,2012,27(1):23-32.］

［13］Zhang L,Li X S,Yuan Q Z,et al.Object-based Approach to National Land Cover Mapping Using HJ Satellite Imagery［J］.Journal of Applied Remote Sensing,2014,8(1):1-19.［14］Blaschke T,Hay G J,Kelly M,et al.Geographic Object-based Image Analysis-towards a New Paradigm［J］.ISPRS Journal of Photogrammetry and Remote Sensing,2014,87:180-191.

［15］Han Tingting,Xi Xiaohuan,Wang Cheng,et al.Study of Forest Classification in Yunnan based on Decision Tree Algorithm［J］.Remote Sensing Technology and Application,2014,29(5):744-751.［韩婷婷,习晓环,王成,等.基于决策树方法的云南省森林分类研究［J］.遥感技术与应用,2014,29(5):744-751.］

［16］Corcoran J M,Knight J F,Gallant A L.Influence of Multi-Source and Multi-temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota［J］.Remote Sensing,2013,5(7):3212-3238.

［17］Giri C,Pengra B,Long J,et al.Next Generation of Global Land Cover Characterization,Mapping,and Monitoring［J］.International Journal of Applied Earth Observation and Geoinformation,2013,25:30-37.

[1]	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.
[2]	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.
[3]	田峰，陈冬花，黄新利，李虎，姚国慧. 基于形态学阴影指数的高分二号影像建筑物高度估计#br#[J]. 遥感技术与应用, 2017, 32(5): 844-850.
[4]	林齐根，邹振华，祝瑛琦，王瑛. 基于光谱、空间和形态特征的面向对象滑坡识别[J]. 遥感技术与应用, 2017, 32(5): 931-937.
[5]	姬忠林，张月平，李乔玄，刘绍贵，李淑娟，任红艳. 基于GF-1影像的冬小麦和油菜种植信息提取[J]. 遥感技术与应用, 2017, 32(4): 760-765.
[6]	王苏芸，孙中昶，郭华东，申维. 基于面向对象的东营市城乡建设用地信息提取[J]. 遥感技术与应用, 2017, 32(4): 780-786.
[7]	施佩荣，陈永富，刘华，吴云华，魏新，钟泽兵. 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.
[8]	姜萍，刘修国，陈启浩，邵芳芳. 利用多尺度SVM-CRF模型的极化SAR图像建筑物提取[J]. 遥感技术与应用, 2017, 32(3): 475-482.
[9]	朱钟正，陈玉福，朱文泉，郑周涛. 适用于多目标遥感自动解译的最佳专题指数筛选[J]. 遥感技术与应用, 2017, 32(3): 564-574.
[10]	郝泷,陈永富，刘华，朱雪林，达哇扎西，李伟娜. 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.
[11]	邓滢,张红,王超,刘萌. 结合纹理与极化分解的面向对象极化SAR水体提取方法[J]. 遥感技术与应用, 2016, 31(4): 714-723.
[12]	王娟,廖静娟,沈国状,许涛. 基于面向对象技术的鄱阳湖湿地地物分类研究[J]. 遥感技术与应用, 2016, 31(3): 543-550.
[13]	王嘉芃,刘婷,俞志强,胡潭高,张登荣,寻丹丹,王冬海. 基于COSMOＧSkyMed和SPOTＧ５的城镇洪水淹没信息快速提取研究[J]. 遥感技术与应用, 2016, 31(3): 564-571.
[14]	宋亚婷,江东,黄耀欢,万华伟. 基于面向对象方法的露天煤矿用地类型提取优先级分析[J]. 遥感技术与应用, 2016, 31(3): 572-579.
[15]	满卫东,李春景,王宗明,贾明明,毛德华,刘明月,路春燕. 基于面向对象分类方法的乌苏里江流域中俄跨境区域湿地景观动态研究[J]. 遥感技术与应用, 2016, 31(2): 378-387.

Viewed

Full text

Abstract

Cited

Shared

Discussed