摘要: 多层感知神经网络(MLP)是主流的非线性分解方法,但是目前缺乏有效方法处理MLP分解结果中的丰度负值问题。为此,提出一种可变神经网络结构的方法,逐步去除负值丰度对应的端元,并调整相应的网络结构使之针对剩余的端元进行分解。通过武汉地区模拟TM遥感影像实验可以发现,该方法与传统MLP方法以及线性光谱分解方法的平均误差分别为0.077 7、0.081 9、0.094 3,说明该方法的分解精度高于其他2种分解方法,能克服丰度负值问题。
关键词:
遥感,
混合像元,
神经网络,
多层感知网络,
非负约束,
非线性光谱分解模型
Abstract: Spectral unmixing of remote sensing images is a hotspot in remote sensing field, and Multilayer Perception(MLP) neural network is a common nonlinear spectral unmixing algorithm. However, currently there is no effective way to deal with the negative abundances derived by the network. To solve this problem, a MLP neural network with variable architecture is proposed. By discarding endmembers with negative abundances, the MLP architecture is modified to unmix the rest endmembers, so a remote sensing image is finally unmixed. An experiment using a simulated TM image shows that the average errors of the proposed method, conventional MLP method and linear spectral unmixing model are 0.077 7, 0.081 9 and 0.094 3 respectively, thus the proposed method outperforms the other two. Therefore, the proposed method can overcome the negative abundance problem effectively.
Key words:
remote sensing,
mixed pixel,
neural network,
Multilayer Perception(MLP) network,
nonnegative constraint,
nonlinear spectral unmixing model
中图分类号:
李熙 , 石长民, 李畅, 陈锋锐, 田礼乔. 可变神经网络结构下的遥感影像光谱分解方法[J]. 计算机工程, 2012, 38(9): 1-3.
LI Xi- , DAN Chang-Min, LI Chang, CHEN Feng-Dui, TIAN Li-Jiao. Spectral Unmixing Method of Remote Sensing Images in Variable Architecture of Neural Network[J]. Computer Engineering, 2012, 38(9): 1-3.