神经网络和知识推理结合的卫星影像分层提取方法研究

Layered Extraction of Satellite Sensing Data Based on NeuralNetwork and Knowledge Reasoning Methodology

提出一种基于神经网络和知识处理的卫星影像分层提取新方法,实现了水系、公路和其他面状地物的分层智能提取。它先用神经网络和基于像元的知识后处理方法提取水系和公路等地物,再通过图像处理方法,将其从原始图像中去除,然后再用神经网络模型分割其他面状地物,统计各斑块的纹理、高程、坡度、形状等特征,采用基于斑块的不确定推理方法分类。最后实验表明新方法优于传统的神经网络方法,而且避免了知识推理方法的复杂性。

A new classification method for satellite sensing data is proposed by using both a neural network and knowledge reasoning technique. It fulfils layered intelligent extraction of water, road and other planelike object for satellite sensing image. It firstly extracts water and road information by neural network and pixelbased knowledge postprocessing method, then removes them from original image, and then segments other planelike object by neural network model, and respectively computes their features, including texture, elevation, slope, shape etc., then extracts them by polygonbased uncertain reasoning method. At last experimental results indicate that the new method outperforms the single neural network method and moreover avoids the complexity of single knowledge reasoning technique.