基于Geoeye-1影像光谱特性的红树林冠层种类识别

基于Geoeye-1高空间分辨率影像与冠层实测高光谱数据，以广西北部湾五种红树群落为研究对象，分析影像光谱用于冠层种类识别的能力。首先研究红树林冠层光谱响应特征，再针对影像采用高光谱分析方法提取端元，结合实测训练样本进行不同方法的识别对比。结果表明：350～1 100 nm谱段内以435，469，523，677，751和761 nm为中心波段的红树群落冠层光谱表现最佳;木榄端元应用识别精度高于实测训练样本应用结果;光谱角制图法能够克服多光谱波段对全色波段分辨率的影响，并有效获取冠层轮廓。利用Geoeye-1影像光谱信息可有效识别三种红树植被，种类最高识别精度达93.03%。研究证实高空间分辨率影像光谱信息的重要性，从机理和应用角度为面向对象红树林种类识别提供了依据和参考。

Mangrove Canopy Species Discrimination Based on Spectral Features of Geoeye-1 Imagery

Based on Geoeye-1 high spatial resolution images and field canopy hyperspectral reflectance of five mangrove communities located at Beibu Gulf, this paper verified the capability of Geoeye-1 imagery for mangrove canopy species identification by utilizing spectral information. The research investigated that: (1) in the spectrum range between 350 and 1 100 nm, the mangrove canopy reflectance exhibited optimum separability in six wavebands (435, 469, 523, 677, 751 and 761 nm); (2) three mangrove species could be effectively identified through the pixel-based spectrum operation, while the Bruguiera acquired the highest producer accuracy up to 93.03%; (3) species end member of Bruguiera extracted directly from the combined imagery conducted on hyperspectral hypothesis performed higher precision than the field training samples behaved. The spectrum significance of the high spatial resolution image was approved, and reference and basis were also illustrated for the further mangrove species distinguishing from the object-oriented perspective.