基于GF-2影像对恰西国家森林公园的遥感分类

doi:10.6048/j.issn.1001-4330.2020.07.017

摘要/Abstract

摘要： 【目的】 选用面向对象的监督分类法,对研究区域的天山云杉林进行遥感分类,选取一种分类效果最佳的方法,为该区域的林地资源调查、动态监测评价提供依据。【方法】 基于高分二号(GF-2)遥感影像数据,借助ESP 尺度评价工具和目视解译相结合,筛选研究区各地物最优分割尺度,利用3种不同分类方法在此基础上进行遥感分类。【结果】 研究区内的水体、道路、其他用地、林地和草地的最优分割尺度,分别为390、372、316、296、246;其次在各地物最优分割尺度下,比较最邻近分类、结合矢量数据分类和阈值分类3种方法,经过精度评估发现,3种分类方法的 Kappa 系数和总体精度值分别为0.760 7、0.782 0、0.840 6和0.814 8、0.830 5、0.876 5。【结论】 阈值分类方法优于其他2种方法,选用更为优良的阈值分类方法引入解决该地区林地资源调查是可行的。

关键词: GF-2影像; 面向对象; 多尺度分割; 分类

Abstract: 【Objective】 To select the object-oriented supervised classification method for remote sensing classification of spruce forest in Tianshan Mountain, and to select a method with the best classification effect in the hope of providing the basis for the investigation of forest land resources and dynamic monitoring and evaluation in this area. 【Methods】 Based on GF-2 remote sensing image data, the optimal segmentation scale of objects in the study area was screened by the combination of ESP scale evaluation tool and visual interpretation. On the basis of three different classification methods, remote sensing classification was conducted. 【Results】 The optimal segmentation scales of water body, road, other land, forest land and grassland in the study area were 390, 372, 316, 296 and 246, respectively. Secondly, under the optimal segmentation scale of local objects, compared with the nearest neighbor classification, combined with vector data classification and threshold classification, it was found that the Kappa coefficient and overall precision of the three classification methods were 0.760,7, 0.782,0, 0.840,6 and 0.814,8, 0.830,5 and 0.876,5, respectively. 【Conclusion】 The threshold classification method is superior to the other two classification methods, which indicates that it is feasible to select a better threshold classification method to solve the problem of forest land resources investigation in this area.

Key words: GF-2 image; object-oriented; multi-scale segmentation; classification

中图分类号:

S771.8

师玉霞, 王振锡, 杨勇强, 连玲, 高亚利. 基于GF-2影像对恰西国家森林公园的遥感分类[J]. 新疆农业科学, 2020, 57(7): 1321-1329.

SHI Yuxia, WANG Zhenxi, YANG Yongqiang, LIAN Ling, GAO Yali. Study on the Classification of Qiaxi National Forest Park Based on the GF-2 Image[J]. Xinjiang Agricultural Sciences, 2020, 57(7): 1321-1329.

参考文献

[1] 禹思慧, 王振锡, 王雅佩, 等. 高强度采伐对天山云杉更新群落物种组成的影响[J]. 新疆农业科学, 2018, 55(7): 1274-1285.
YU Sihui, WANG Zhenxi, WANG Yapei, et al. Effects of High Intensity Cutting on Species Composition of Picea Schrenkiana. var tianshanica Regeneration Community[J]. Xinjiang Agricultural Sciences, 2018, 55(7): 1274-1285.
[2] 王慧贤, 靳惠佳, 王娇龙, 等. K均值聚类引导的遥感影像多尺度分割优化方法[J]. 测绘学报, 2015,44(5):526-532.
WANG Huijia, JIN Huijia, WANG Jiaolong, et al. Optimization Approach for Multi-scale Segmentation of Remotely Sensed Imagery Under K-means Clustering Guidance [J]. Acta Ueodaetica et Cartographica Sinica, 2015,44(5):526-532.
[3] 常春艳, 赵庚星, 工凌, 等. 滨海光谱混淆区面向对象的土地利用遥感分类[J]. 农业工程学报, 2012, 28(5):226-231
CHANG Chunyan, ZHAO Gengxing, GONG Ling, et al. Land Use Classification Based on RS Object-oriented Method in Coastal Spectral Confusion Region [J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(5):226-231.
[4] 路春燕, 高弋斌, 陈远丽, 等. 基于RS/GIS的泉州湾红树林湿地时空动态变化分析[J]. 森林与环境学报, 2019, 39(2):143-152.
LU Chunyan, GAO Gebin, CHEN Yuanli, et al. Dynamic Change Analysis of Mangrove Swamps Based on RS/GIS in Quanzhou Bay[J]. Journal of Forest and Environment, 2019, 39(2): 143-152.
[5] 林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报, 2017, 46 (5): 724-733.
LIN Xiangguo, ZHANG Jixian. Object-based Morphological Building Index for Building Extraction from High Resolution Remote Sensin Imagery [J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(5):724-733.
[6] 苏簪铀, 邱炳文, 陈崇成. 基于面向对象分类技术的景观信息提取研究[J]. 遥感信息, 2009, 10(2):42-46.
SU Zanyou, QIU Bingwen, CHEN Chongcheng. Study on Extraction of Landscape Information Based on the Object-oriented Classification Techniques [J]. Remote Sensing Information, 2009, 10(2):42-46.
[7] 高闪闪, 陈仁喜. 辅以纹理特征的植被分类方法研究[J]. 科学技术与工程, 2013, 13(29):8672-8677,8696.
GAO Shanshan, CHEN Renxi. The Research of Vegetation Classification Method with Texture Feature [J]. Science Technology and Engineering, 2013,13(29):8672-8677,8696.
[8] 吕利利, 颉耀文, 黄晓君, 等.基于CART决策树分类的沙漠化信息提取方法研究[J].遥感技术与应用, 2017,32(3):499-506.
L Lili, XIE Yaowen, HUANG Xiaojun, et al. Desertification Information Extraction Method Research Based on the CART Decision Tree Classification[J].Remote Sensing Technology and Application,2017,32(3):499-506.
[9] 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.
Han Tingting, Xi Xiaohuan, Wang Cheng, et al. Study on Forest Classification in Yunnan Based on Decisional Tree Algorithm [J].Remote Sensing Technology Application, 2014,29(5):744-751.
[10] 吴庆岗, 赵伊兰, 黄伟, 等.基于改进自适应阈值局部三值模式的遥感图像分类[J].科学技术与工程,2019,19(12):242-247.
WU Qinggang, ZHAO Yilan, HUANG Wei. Remote Sensing Image Classification Based on Modified Adaptive Threshold Local Ternary Pattern [J]. Science Technology and Engineering, 2019,19(12):242-247.
[11] 宋明辉. 基于高分二号数据的面向对象城市土地利用分类研究[J]. 遥感技术与应用, 2019,34(3):547-552,629.
SONG Minghui. Object-oriented Urban Land Classification with GF-2 Remote Sensing Image [J]. Remote Sensing Technology and Application, 2019,34(3):547-552,629.
[12] 刘海伟. 图像分类与变化检测方法的研究与实现[D]. 北京: 北方工业大学, 2013.
LIU Haiwei. Research and Implementation on Classification and Change Detection Method [D]. Beijing: North China University of Technology, 2013.
[13] Milansonka, Vaclavhiavac, Rogerboyie. Image Processing, Analysis, and Machine Vision [M]. Thomson Brooks/Cole.2002.
[14] Navulur K. Multispectral Image Analysis Using the Object-Oriented Paradigm [J]. Crc Press, 33(1): C24-C.
[15] Dragut L, Csillik O, Eisank C, et al. Automated Parameterization for Multi Scale Image Segmentation on Multiple Layers [J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2014,88: 119-127.
[16] 王芳, 王建, 谢兵, 等. 一种遥感影像自适应分割尺度的分类方法[J]. 测绘科学,2019,(11):1-12.
WANG Fang, WANG Jian, XIE Bing, et al. A Classification Method for Adaptive Segmentation Scale of Remote Sensing Images [J]. Science of Surveying and Mapping, 2019,(11):1-12.
[17] 葛春青, 张凌寒, 杨杰. 基于决策树规则的面向对象遥感影像分类[J]. 遥感信息, 2009, 4(3): 7-8.
GE Chunqing, ZHANG Linghan, YANG Jie. Object-oriented Classification of Remote Sensing Image Based on Decision Trees [J]. Remote Sensing Information, 2009, 4(3):7-8.
[18] 李亮, 王蕾, 孙晓鹏, 等. 面向对象变化向量分析的遥感影像变化检测[J]. 遥感信息, 2017, 32(6): 71-73.
LI Liang, WANG Lei, SUN Xiaopeng, et al. Remote Sensing Change Detection Method Based on Object-oriented Change Vector Analysis[J].Remote Sensing Information, 2017,32(6):71-73.
[19] 祝锦霞, 王坷. 面向对象的高分辨率影像变化检测方法研究[J]. 农业机械学报, 2013, 44(4): 185-186.
ZHU Jinxia, WANG Ke. Object-oriented Change Detection Method Using Very High Spatial Resolution Imagery [J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(4): 185-186.
[20] 左世欧. 基于RS与GIS的南涧县土地覆被监测研宄[D]. 昆明: 云南师范大学, 2016.
ZUO Shiou. A Study on Land Cover Monitoring in Nanjian County Based on RS and GIS [D]. Qunming:Yunnan Normal University, 2016.
[21] 马宗义. 基于TM影像的沙漠化信息定量提取方法[D]. 兰州: 兰州大学, 2013.
MA Zongyi. Quantitative Method for Extracting of Desertification Information Based on TM [D]. Lanzhou: Lanzhou University, 2013.
[22] 唐建华. 基于多源数据的目标特征库建立与自然资源资产信息提取方法研究[D]. 成都: 西南交通大学, 2015.
TANG Jian-hua. Establishment of Target Feature Library Based on Multi-resource Data and the Research of Extraction Method of Natural Resource Asset Information [D]. Chengdu: Southwest Jiaotong University,2015.
[23] 李天坤. 基于面向对象分类方法的烟草种植面积提取研究[D]. 雅安: 四川农业大学, 2013.
LI Tiankun. The Research of Extracted tobacco Planting Area Based on Object-oriented Classification Method[D]. Ya’an: Sichuan Agricultural University, 2013.
[24] 任金桐, 杨武年, 邓晓宇, 等. 基于OIF和最优尺度分割的GF-2影像分类适用性研究[J]. 现代电子技术, 2018, 41(8): 72-82.
REN Jintong, YANG Wunian, DENG Xiaoyu, et al. Research on Applicability of GF-2 Images Classification Based on OIF and Optimal Scale Segmentation [J]. Modern Electronics Technique, 2018, 41(8): 72-82.
[25] 崔宾阁, 吴亚男, 钟勇, 等.高光谱图像滚动引导递归滤波与地物分类[J]. 遥感学报,2019,23(4):431-442.
CUI Binge, WU Yanan, ZHONG Yong, et al. Hyperspectral Image Rolling Guidance Recursive Filtering and Classification [J]. Journal of Remote Sensing, 2019,23(3): 431-442.
[26] 徐乔, 张霄, 余绍淮, 等. 综合多特征的极化SAR图像随机森林分类算法[J]. 遥感学报,2019,23(4):685-694.
XU Qiao, ZHANG Xiao, YU Shaohuai, et al. Multi-feature-based Classification Method Using Random Forest and Superpixels for Polarimetric SAR Images [J]. Journal of Remote Sensing, 2019,23(4): 685-694.
[27] 马浩然, 赵天忠, 曾怡. 面向对象的最优分割尺度下多层次森林植被分类[J]. 东北林业大学学报, 2014,42(9):52-57.
MA Haoran, ZHAO Tianzhong, ZENG Yi. Object-based Multi-level Classification of Forest Vegetation on Optimal Segmentation Scale [J]. Journal of Northeast Forestry University, 2014,42(9):52-57.
[28] 林志玮, 丁启禄, 涂伟豪, 等. 基于多元HoG及无人机航拍图像的植被类型识别[J]. 森林与环境学报, 2018, 38(4): 444-450.
LIN Zhiwei, DING Qilu, TU Weihao, et al. Vegetation Type Recognition Based on Multivariate HoG and Aerial Image Captured by UAV[J]. Journal of Forest and Environment, 2018, 38(4): 444-450.
[29] 卢兴. 基于分层次多尺度分割的高分遥感影像分类研究[D]. 抚州: 东华理工大学, 2018.
LU Xing. A Dissertation Submitted to East China University of Technology for Master Degree [D]. Fuzhou: East China University of Technology, 2018.
[30] 李剑. 基于GF-2影像的城区地物信息尺度选择及分类方法研究[D]. 抚州: 东华理工大学, 2018.
LI Jian. Research on Scale Selection and Classification Method of Urban Feature Information Based on GF-2 Image [D].Fuzhou: East China University of Technology, 2018.