The typical vegetation classification at Bosten lakeshore using CR-SAM

ZHANG Zihui; LI Xinguo; LI Yong

doi:10.13471/j.cnki.acta.snus.2021D013

您当前的位置：

首页 >

文章列表页 >

The typical vegetation classification at Bosten lakeshore using CR-SAM

Research articles | 更新时间：2023-11-01

- The typical vegetation classification at Bosten lakeshore using CR-SAM
- Acta Scientiarum Naturalium Universitatis Sunyatseni Vol. 61, Issue 6, Pages: 36-43(2022)
- 作者机构：
  
  1.新疆师范大学地理科学与旅游学院，新疆乌鲁木齐 830054
  2.中国科学院新疆生态与地理研究所，新疆乌鲁木齐 830011
  3.新疆干旱区湖泊环境与资源重点实验室，新疆乌鲁木齐 830054
- 作者简介：
- 基金信息：
- DOI：10.13471/j.cnki.acta.snus.2021D013
  CLC： P237
- Published：25 November 2022，
  
  Published Online：20 April 2022，
  
  Received：28 February 2021，
  
  Accepted：25 June 2021
扫描看全文
张子慧,李新国,李勇.基于CR-SAM的博斯腾湖西岸湖滨带典型植被分类[J].中山大学学报(自然科学版),2022,61(06):36-43.

ZHANG Zihui,LI Xinguo,LI Yong.The typical vegetation classification at Bosten lakeshore using CR-SAM[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2022,61(06):36-43.
张子慧,李新国,李勇.基于CR-SAM的博斯腾湖西岸湖滨带典型植被分类[J].中山大学学报(自然科学版),2022,61(06):36-43. DOI： 10.13471/j.cnki.acta.snus.2021D013.

ZHANG Zihui,LI Xinguo,LI Yong.The typical vegetation classification at Bosten lakeshore using CR-SAM[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2022,61(06):36-43. DOI： 10.13471/j.cnki.acta.snus.2021D013.

摘要

以博斯腾湖西岸湖滨带为研究区，采取高光谱数据和Sentinel-2A遥感数据，采用包络线去除（CR）法提取并分析箭杆杨、沙枣树和芦苇3种典型植被类别间的可区分特征，利用光谱角匹配（SAM）法对研究区3种典型植被的分布状况进行分类识别。结果表明：① SAM分类方法对3种典型植被的识别百分比为58.47%，基于包络线去除的光谱角匹配（CR-SAM）分类方法对3种典型植被的识别百分比为79.12%，CR-SAM能够突出植被光谱细节特征，减少环境背景对植被光谱的影响。② CR-SAM分类结果的总体分类精度为70.50%，较SAM分类方法提高了17.50%，Kappa系数由SAM分类方法的0.32增加到0.66，CR-SAM分类方法更能满足影像分类过程中的精度需求。③ 3种典型植被中，箭杆杨呈片状分布于道路两侧，面积3.98 km

，占研究区总面积的2.01%；沙枣树主要分布于荒地与耕地之间的过渡带，面积19.76 km

，占研究区总面积的9.98%；芦苇主要分布于湖滨带湿地及开都河下游沿岸，面积174.26 km

，占研究区总面积的88.01%。

Abstract

Using hyperspectral data and Sentinel-2A remote sensing image data

the continuum removed (CR) method was adopted to extract and analyze the distinguishable characteristics of typical vegetation species including

Populus nigra

var.

thevestina

(Dode)

Bean

Elaeagnus angustifolia

and

Phragmites australis

in the west shore of Bosten Lake. The typical vegetation covering in the study area was classified and identified by Spectral Angle Mapper (SAM). The results show that three vegetation species are identified 58.47% by SAM and 79.12% by CR-SAM. The detailed characteristics of vegetation spectrums are highlighted and the influence of environmental background on vegetation spectrums is reduced by CR-SAM. The overall accuracy of the CR-SAM classification result is 70.50%

which is 17.5% higher than that of the SAM classification method; the Kappa coefficient increases from 0.32 in SAM to 0.66 in VR-SAM

indicating that CR-SAM satisfies the accuracy requirements better than SAM in the process of image classification. Among the three vegetation species

Populus nigra

var.

thevestina

(Dode)

Bean distributes strictly on both sides of the roads and covers an area of 3.98 km

and 2.01% of the total area of the study area;

E. angustifolia

distributes mainly in the transitional zones between wetlands and cultivated lands and covers an area of 19.76 km

and 9.98% of the total area;

Ph. australis

distributes commonly in the lakeside wetlands and along the lower reaches of the Kaidu River

and covers an area of 174.26 km

and 88.01% of the total area.

关键词

植被分类Sentinel-2A遥感数据高光谱数据包络线去除光谱角制图湖滨带

Keywords

vegetation classificationsentinel-2A remote sensing datahyperspectral datacontinuum removedspectral angle mapperlakeside zone

references

李亭亭，田礼乔，李建，等.基于Sentinel卫星的浑浊水体叶绿素反演对比研究——以鄱阳湖为例［J］.华中师范大学学报（自然科学版），2017，51（6）：858-864.

HIRANO A， MADDEN M， WELCH R. Hyperspectral image data for mapping wetland vegetation ［J］. Wetlands， 2003， 23（2）： 436-448.

曾帅，况润元，肖阳，等.鄱阳湖湿地植物实测高光谱数据分类［J］.遥感信息，2017，32（5）：75-81.

吴见，彭建，王孟和，等.几种常见树种叶片光谱秋季变化特征分析［J］.光谱学与光谱分析，2017，37（4）：1225-1231.

杜培军，夏俊士，薛朝辉，等.高光谱遥感影像分类研究进展［J］.遥感学报，2016，20（2）：236-256.

CEAMANOS X， WASKE B， BENEDIKTSSON J A， et al. A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data［J］. International Journal of Image and Data Fusion， 2010， 1（4）： 293-307.

李凯，陈芸芝，许章华，等.虫害胁迫下毛竹叶绿素含量高光谱估算方法［J］.光谱学与光谱分析，2020，40（8）：2578-2583.

白继伟，赵永超，张兵，等.基于包络线消除的高光谱图像分类方法研究［J］.计算机工程与应用，2003，（13）：88-90+128.

张雪红，刘绍民，何蓓蓓.基于包络线消除法的油菜氮素营养高光谱评价［J］.农业工程学报，2008，24（10）：151-155.

王金龙，李艳红，李发东.博斯腾湖人工和天然芦苇湿地土壤呼吸动态变化规律及其影响因素［J］.农业环境科学学报，2017，36（1）：167-175.

张海燕，刘彬.博斯腾湖湖滨湿地植被数量分类与排序［J］.植物科学学报，2015，33（1）：36-43.

田青林，潘蔚，李瑶，等.基于小波包变换和权重光谱角制图的岩心高光谱蚀变信息提取［J］.国土资源遥感，2019，31（4）：41-46.

岑奕，张艮中，张立福，等.地物光谱不确定性及光谱角制图算法适用性研究［J］.光谱学与光谱分析，2015，35（10）：2841-2845.

王伟超，王慧琴，王可，等.一种基于统计流形的光谱信息散度颜料识别方法［J］.激光与光电子学进展，2018，55（1）：416-423.

夏列钢，王卫红，胡晓东，等.图像分类中基于核映射的光谱匹配度量方法［J］.测绘学报，2012，41（4）：591-596+604.

张甜，廖和平，崔林林.包络线去除的丘陵地区遥感影像阴影信息重建［J］.遥感学报，2017，21（4）：604-613.

CHEN C Q, JIANG Q G, ZHANG Z C, et al. Hyperspectral inversion of petroleum hydrocarbon contents in soil based on continuum removal and wavelet packet decomposition［J］. Sustainability,2020, 12(10): 4218.

明群杰.基于光谱匹配技术的青藏高原典型植被识别与提取［D］.北京：中国地质大学（北京），2017.

周伟，李浩然，石佩琪，等.三江源区毒杂草型退化草地植被光谱特征分析［J］.地球信息科学学报，2020，22（8）：1735-1742.

杨可明，刘飞，孙阳阳，等.谐波分析光谱角制图高光谱影像分类［J］.中国图象图形学报，2015，20（6）：836-844.

姬旭升，李旭，万泽福，等.基于高空间分辨率卫星影像的新疆阿拉尔市棉花与枣树分类［J］.中国农业科学，2019，52（6）：997-1008.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang

Vegetation classification and vegetation map of Neilingding Island in Guangdong Province based on UAV remote sensing technology

Related Author

Zihui ZHANG

Xinguo LI

Yong LI

LI Xinguo

FAN Yongzhuo

YU Shixiao

CHEN Ting

XU Hualin

Related Institution

College of Geographical Sciences and Tourism / Laboratory of Lake Environment and Resources in Arid Regions of Xinjiang， Xinjiang Normal University

School of Life Sciences， Sun Yat-sen University

Research Institute of Sun Yat-sen University in Shenzhen

Guangdong Neilingding-Futian National Nature Reserve

Postal code：510275
Tel：020-84112585，84113223 Email：xuebaozr@mail.sysu.edu.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰