摘要
提出了一种从TM图像上获取芦苇冠层叶面积指数的方法:首先对芦苇的生长背景进行分类;然后,对不同的背景光谱利用冠层反射率(FCR)模型计算得到查找表;最后,利用实测数据和查找表中的数据作为参数进行BP神经网络模型训练,从而得到芦苇冠层LAI。结果表明,人工神经网络方法有很强的非线性拟合能力,能够消除背景对反演结果的影响,有效提高LAI反演的精度。
Rapid and accurate LAI retrieval from a large area is an important research topic in the field of remote sensing. In this paper, a model is presented to estimate LAI of reed canopy from Landsat -5 TM image data. The model first classified the background of reed canopy into soil and water and then calculated and output a lookup table （LUT） by use of FCR model. After that, LAI mapping was conducted based on the BP neural network model, which was trained using the data of actual measurement and LUT. The results indicate that the method has strong nonlinear fitting capability, and can improve the accuracy of LAI results through reducing the background influence from the background spectrum.
出处
《国土资源遥感》
CSCD
2008年第2期62-67,共6页
Remote Sensing for Land & Resources
基金
国家自然科学基金项目(40371081)
南京信息工程大学科研基金资助项目(S8107359001)联合资助
关键词
神经网络
FCR模型
叶面积指数
反演
芦苇
Neural network
FCR model
Leaf Area Index （LAI）
Retrieval
Reed canopy
