[1]刘恺,周小成.采用决策树方法的高分一号PMS影像山区森林覆盖提取[J].华侨大学学报(自然科学版),2019,40(3):376-383.[doi:10.11830/ISSN.1000-5013.201809022]
 LIU Kai,ZHOU Xiaocheng.Forest Cover Extraction From Gaofen-1 PMS Image in Mountain Area Using Decision Tree[J].Journal of Huaqiao University(Natural Science),2019,40(3):376-383.[doi:10.11830/ISSN.1000-5013.201809022]
点击复制

采用决策树方法的高分一号PMS影像山区森林覆盖提取()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第40卷
期数:
2019年第3期
页码:
376-383
栏目:
出版日期:
2019-05-20

文章信息/Info

Title:
Forest Cover Extraction From Gaofen-1 PMS Image in Mountain Area Using Decision Tree
文章编号:
1000-5013(2019)03-0376-08
作者:
刘恺12 周小成12
1. 福州大学 卫星空间信息技术综合应用国家地方联合工程研究中心, 福建 福州 350108;2. 福州大学 空间数据挖掘与信息共享教育部重点实验室, 福建 福州 350108
Author(s):
LIU Kai12 ZHOU Xiaocheng12
1. National and Local Joint Engineering Research Center of Satellite Geospatial Information Technology, Fuzhou University, Fuzhou 350108, China; 2. Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University,
关键词:
山区 森林覆盖 决策树模型 面向对象 高分一号
Keywords:
mountain area forest cover decision tree model object oriented gaofen-1 satellite
分类号:
TP79
DOI:
10.11830/ISSN.1000-5013.201809022
文献标志码:
A
摘要:
以福建省龙岩市新罗区为例,选取单期国产高分一号(GF-1)PMS影像,采用面向对象决策树模型进行森林覆盖提取.针对山区地形因素引起的阴坡森林区域光谱值异常现象,灵活运用坡度因子、红绿比值植被指数、比值植被指数、归一化水体指数特征进行森林覆盖提取,并将该方法与其他分类器算法进行对比.结果表明:决策树模型的森林制图精度为96.1%,Kappa系数为0.84;该模型可提取高精度的山区森林覆盖信息,且具有可靠性.
Abstract:
Taking Xinluo District, Longyan City, Fujian Province as an example, a single phase domestic gaofen-1 satellite(GF-1)PMS image was selected, and an object-oriented decision tree model was used for forest cover extraction. Aiming at the anomalous optical spectral value of shady forest area caused by mountainous terrain factors, the slope coverage, red-green ratio vegetation index, ratio vegetation index and normalized water body index are used to extract forest cover, and the used method is combined with other classifier algorithms comparing. The results show that the forest mapping accuracy of the decision tree model is 96.1%, and the Kappa coefficient is 0.84. This model can extract high-precision mountain forest coverage information with reliability.

参考文献/References:

[1] HANSEN M C,POTAPOV P V,MOORE R,et al.High-resolution global maps of 21st-century forest cover change[J].Science,2014,344(6187):850.DOI:10.1126/science.1244693.
[2] 黄健熙,侯矞焯,苏伟,等.基于GF-1 WFV数据的玉米与大豆种植面积提取方法[J].农业工程学报,2017,33(7):164-170.DOI:10.11975/j.issn.1002-6819.2017.07.021.
[3] YANG Yanjun,HUANG Yan,TIAN Qingjiu,et al.The extraction model of paddy rice information based on GF-1 satellite WFV images[J].Spectroscopy and Spectral Analysis,2015,35(11):3255-3261.DOI:10.3964/j.issn.1000-0593(2015)11-3255-07.
[4] 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(6):31-36.DOI:10.3969/j.issn.1000-3177.2015.06.006.
[5] 牛增懿,丁建丽,李艳华,等.基于高分一号影像的土壤盐渍化信息提取方法[J].干旱区地理,2016,39(1):171-181.
[6] 田海峰,周伯燕,陈燕芬,等.县域尺度上基于GF-1 PMS影像的冬小麦种植面积遥感监测[J].中国农业大学学报,2017,22(10):139-146.DOI:10.11841/j.issn.1007-4333.2017.10.17.
[7] 林熙,罗小军,郭红梅,等.基于语义约束的GF-1遥感影像山区居民地提取方法[J].山地学报,2017,35(1):102-111.DOI:10.16089/j.cnki.1008-2786.000201.
[8] 徐磊,巫兆聪,罗飞,等.基于GF-1/WFV与MODIS时空融合的森林覆盖定量提取[J].农业机械学报,2017,48(7):145-152.DOI:10.6041/j.issn.1000-1298.2017.07.018.
[9] 尹凌宇,覃先林,孙桂芬,等.利用KPCA法检测高分一号影像中的森林覆盖变化[J].国土资源遥感,2018,30(1):95-101.DOI:10.6046/gtzyyg.2018.01.13.
[10] 任冲,鞠洪波,张怀清,等.多源数据类型的精细分类方法[J].林业科学,2016,52(6):54-65.DOI:10.11707/j.100 1-7488.20160607.
[11] MCIVER D K,FRIEDL M A.Using prior probabilities in decision-tree classification of remotely sensed data[J].Remote Sensing of Environment,2002,81(2):253-261.DOI:10.1016/s0034-4257(02)00003-2.
[12] 陈利,林辉,孙华,等.基于决策树分类的森林信息提取研究[J].中南林业科技大学学报,2013,33(1):46-51.
[13] 杨存建,周其林,任小兰,等.基于多时相MODIS数据的四川省森林植被类型信息提取[J].自然资源学报,2014(3):507-515.DOI:10.11849/zrzyxb.2014.03.014.
[14] 罗朝沁,林辉,孙华,等.基于MODIS影像大尺度森林资源信息提取方法研究[J].中南林业科技大学学报,2015(11):21-26.DOI:10.14067/j.cnki.1673-923x.2015.11.005.
[15] 徐伟燕,孙睿,金志凤.基于资源三号卫星影像的茶树种植区提取[J].农业工程学报,2016(增刊1):161-168.
[16] 任传帅,叶回春,崔贝,等.基于面向对象分类的芒果林遥感提取方法研究[J].资源科学,2017,39(8):1584-1591.DOI:10.18402/resci.2017.08.14.
[17] ZHAO Jinling,GUO Junjie,CHENG Wenjie,et al.Assessment of SPOT-6 optical remote sensing data against GF-1 using NNDiffuse image fusion algorithm[J].Modern Physics Letters B,2017,31(19/20/21):1740043.DOI:10.1142/S0217984917400437.
[18] GAO Yan,MAS J F,KERLE N,et al.Optimal region growing segmentation and its effect on classification accuracy[J].International Journal of Remote Sensing,2011,32(13):3747-3763.DOI:10.1080/01431161003777189.
[19] BLASCHKE T,HAY G J.Object-oriented image analysis and scale-space: Theory and methods for modeling and evaluating multi-scale landscape structure[J].International Archives of Photogrammetry and Remote Sensing,2001,34:22-29.
[20] WHITESIDE T G,BOGGS G S,MAIER S W.Comparing object-based and pixel-based classifications for mapping savannas[J].2011,13(6):884-893.DOI:10.1016/j.jag.2011.06.008.
[21] DR?GUT L,CSILLIK O,EISANK C,et al.Automated parameterisation for multi-scale image segmentation on multiple layers[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,88(100):119-127.
[22] TRIMBLE.Cognition developed reference book[M].Munich:Trimble Germany GmbH,2014.

备注/Memo

备注/Memo:
收稿日期: 2018-09-11
通信作者: 周小成(1977-),男,副研究员,博士,主要从事高分辨率遥感影像信息提取的研究.E-mail:zhouxc@fzu.edu.cn.
基金项目: 中央引导地方科技发展专项(2017L3012); 福建省自然科学基金资助项目(2015H6008)
更新日期/Last Update: 2019-05-20