基于主成分分析和植被指数的潮滩植被信息提取研究

Vegetation Information Extraction in the Tide-land Based on Principal Component Analysis and Vegetation Indices

针对潮滩湿地植被的特点,利用2004年7月30日的SPOT5数据,在主成分分析的基础上,结合归一化植被指数NDVI和归一化水体指数NDWI,进行了Brovey变换和小波变换融合处理。融合后得到的图像较融合前的图像和原始SPOT5图像在空间相关性、信息熵以及植被间的可分离度等指标上都有显著的提高。对融合效果较佳的基于NDWI和主成分的小波变换的图像进行最大似然法分类,与原始图像最大似然法分类结果相比,分类精度提高了4.41%。

According to the characteristics of wetland vegetation,the paper carried out the Brovey transform and the wavelet transform fusion to SPOT 5 data on July 30,2007,combined with the normalized difference vegetation index（NDVI） and the normalized difference water index（NDWI） based on principal component analysis.The fused images are improved significantly in compare with the un-fused images and the original images in some indicators such as the spatial correlation,entropy and the separability of different vegetations.The paper used the maximum likelihood method to classify the original image and the better fused image based on the wavelet transform of NDWI and principal component analysis.Compared with the classification result of the original images,the classification accuracy of the fused image increased 4.41%.