摘要
利用冠层光谱反射率数据(Rλ),对处于果实成熟期的七种挂果果树的树种进行了辨识研究。通过光谱数据重采样、植被指数求算等相关数据处理,比较了六种卫星传感器与四种植被指数对果树树种的辨识效能,并在优选数据形式、优化模型参数的基础上,建立了辨识果树树种的BP神经网络模型。主要结论为:(1)六种卫星传感器辨识果树树种的效能由强到弱的排列顺序为:MODIS,ASTER,ETM+,HRG,QUICKBIRD,IKONOS;(2)在四种植被指数中,RVI对果树树种的辨识效能最强,其次是NDVI,SAVI与DVI的辨识效能相对较弱;(3)用MODIS或ETM+传感器的近红外通道与红光通道上的反射率数据,求算的RVI与NDVI对果树树种的辨识效能相对较强;(4)在Rλ及其22种变换数据中,波长间隔设为9 nm的d1[log(1/Rλ)],是建立BP神经网络模型的首选数据形式;(5)利用波长间隔设为9 nm的d1[log(1/Rλ)]这一数据形式,建立了辨识果树树种的3层BP神经网络模型。
Using the spectral reflectance data （Rλ） of canopies, the present paper identifies seven species of fruit trees bearing fruit in the fruit mature period. Firstly, it compares the fruit tree species identification capability of six kinds of satellite sensors and four kinds of vegetation index through re-sampling the spectral data with six kinds of pre-defined filter function and the relat- ed data processing of calculating vegetation indexes. Then, it structures a BP neural network model for identifying seven species of fruit trees on the basis of choosing the best transformation of Rλ and optimizing the model parameters. The main conclusions are： （1） the order of the identification capability of the six kinds of satellite sensors from strong to weak is： MODIS, ASTER, ETM＋, HRG, QUICKBIRD and IKONOS; （2） among the four kinds of vegetation indexes, the identification capability of RVI is the most powerful, the next is NDVI, while the identification capability of SAVI or DVI is relatively weak; （3） The identification capability of RVI and NDVI calculated with the reflectance of near-infrared and red channels of ETM＋ or MODIS sensor is relatively powerful; （4） Among Rλ and its 22 kinds of transformation data, d^1 [log（1/Rλ）] （derivative gap is set 9 nm） is the best transformation for structuring BP neural network model; （5） The paper structures a 3-layer BP neural network model for identifying seven species of fruit trees using the best transformation of Rλ which is d^1 [-log（1/Rλ）]（derivative gap is set 9 nm）.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2009年第7期1937-1940,共4页
Spectroscopy and Spectral Analysis
基金
国家自然科学基金项目(30872073)
国家重复基础研究发展计划"973"项目(2007CB407203)资助
关键词
光谱分析
果树树种
辨识
卫星传感器
植被指数
BP神经网络模型
Spectral analysis
Species of fruit trees
Identification
Satellite sensor
Vegetation index
BP neural network model
