黄河口湿地典型地物类型高光谱分类方法

王建步; 张杰; 马毅; 任广波

doi:10.3969/j.issn.1001-909X.2014.03.005

PDF(2221 KB)

海洋学研究 ›› 2014, Vol. 32 ›› Issue (3) : 36-41. DOI: 10.3969/j.issn.1001-909X.2014.03.005

研究论文

黄河口湿地典型地物类型高光谱分类方法

王建步, 张杰, 马毅, 任广波

作者信息 +

Classification method of hyperspectral image in typical surface feature of Huanghe River estuary wetland

WANG Jian-bu, ZHANG Jie, MA Yi, REN Guang-bo

Author information +

文章历史 +

摘要

黄河口湿地地物类型具有复杂多样的特点,本文将线性光谱混合分析模型与归一化植被指数(NDVI)和归一化水体指数(NDWI)相结合,建立了一种新的滨海湿地遥感影像分类方法;开展了基于CHRIS高光谱影像的黄河口湿地芦苇、柽柳、碱蓬、大米草、潮滩和水体6种典型地物分类实验,整体分类精度为77.33%,Kappa 系数为 0.71,与经典的最大似然分类(MLC)方法相比较,整体分类精度提高1.6%,Kappa 系数提高0.02,尤其是芦苇、碱蓬、大米草和潮滩的分类精度明显提高。

Abstract

The typical surface feature of Huanghe River estuary wetland is complex and diverse. In this study, a new classification model for coast wetland remote image was constructed using the linear spectral mixture analysis model, combined with normalized difference vegetation index(NDVI) and normalized difference water index(NDWI). Based on CHRIS hyperspectral image, a classification test of Huanghe River estuary wetland was carried, which consisted of 6 kinds of typical objects: phragmites, tamarix chinesis, suaeda, spartina, tidal flat and water, The results show that the overall accuracy of the combined model is 77.33%, and Kappa coefficient is 0.71, increasing 1.6% and 0.02 respectively compared with that from the classical MLC method, and especially, a better classification accuracy is obtained obviously for phragmites, suaeda, spartina and tidal flat.

导出引用

王建步, 张杰, 马毅, 任广波. 黄河口湿地典型地物类型高光谱分类方法[J]. 海洋学研究. 2014, 32(3): 36-41 https://doi.org/10.3969/j.issn.1001-909X.2014.03.005

WANG Jian-bu, ZHANG Jie, MA Yi, REN Guang-bo. Classification method of hyperspectral image in typical surface feature of Huanghe River estuary wetland[J]. Journal of Marine Sciences. 2014, 32(3): 36-41 https://doi.org/10.3969/j.issn.1001-909X.2014.03.005

中图分类号： TP753

参考文献

[1] WOODWARD R T,WUI Y S. The economic value of wetland services: A meta-analysis[J].Ecological Economics,2001,37(2):257-270.
[2] YANG Yong-xing. Main characteristics,progress and prospect of international wetland science research[J]. Process in Geography,2002,21(2):111-120.
杨永兴. 国际湿地科学研究的主要特点、进展与展望[J].地理科学进展,2002,21(2):111-120.
[3] ROSSO P H, USTIN S L, HASTINGS A. Mapping marshland vegetation of SanFrancisco Bay, California, using hyperspectral data[J]. International Journal of Remote Sensing,2005,26(23):5 169-5 191.
[4] LI L,USTIN S L, LAY M. Application of multiple endmember spectral mixture analysis(MESMA) to AVIRIS imagery for coastal salt marsh mapping: A case study in China Camp, CA, USA[J]. International Journal of Remote Sensing,2005,26(23):5 193-5 207.
[5] HE Mei-mei, ZHAO Bin, OUYANGA Z T, et al. Linear spectral mixture analysis of Landsat TM data for monitoring invasive exotic plants in estuarine wetlands[J]. International Journal of Remote Sensing,2010,31(16):4 319-4 333.
[6] WU Jian, PENG Dao-li. Wetland information extraction based on improved linear spectral mixture model[J]. Jounal of China Agricultural University,2011,16(3):140-144.
吴见,彭道黎. 改进线性光谱混合分解模型湿地信息提取[J]. 中国农业大学学报,2011,16(3):140-144.
[7] CUI Tian-xiang,GONG Zhao-ning,ZHAO Wen-ji, et al. Research on estimating wetland vegetation abundance based on spectral mixture analysis with different endmember model: A case study in Wild Duck Lake, wetland,Beijing[J]. Acta Ecologic Sinica,2013,33(4):1 160-1 171.
崔天翔,宫兆宁,赵文吉, 等. 不同端元模型下湿地植被覆盖度的提取方法——以北京市野鸭湖湿地自然保护区为例[J]. 生态学报,2013,33(4):1 160-1 171.
[8]MICHISHITA R, GONG Peng, XU Bing. Spectral mixture analysis for bi-sensor wetland mapping using Landsat TM and Terra MODIS data[J]. International Journal of Remote Sensing,2012,33(11): 3 373-3 401.
[9] ZHANG Yin-long, LU Deng-sheng, YANG Bo, et al. Coastal wetland vegetation classification with a Landsat thematic mapper image[J]. International Journal of Remote Sensing,2011,32(2):545-561.