行程长度纹理特征在SPOT遥感图像分类中的应用

Application of Run-Length Texture Features to SPOT Remote Sensing Image Classification

将行程长度纹理特征与神经网络相结合应用于遥感图像分类中.在特征选择阶段采用类内、类间方差标准与 Rough 集相结合的方法挑选出有较强分类能力的特征并有效去除冗余特征.针对高分辨率、大尺度的 SPOT全色遥感卫星图像,分别基于行程长度纹理特征、共生矩阵纹理特征、灰度-梯度共生矩阵纹理特征和灰度-平滑共生矩阵纹理特征,采用 BP、RBF 两种类型的神经网络以及最近邻分类算法(K-NN 法)对其进行分类,并对分类结果进行对比.实验结果证明本文算法的有效性.

Combined with neural network, a method for remote sensing image classification based on run-length features is proposed. According to the criterion of variances between and intra classes, the efficient features are selected and the redundant ones are excluded successfully by the method of rough set. Run- length features, co- occurrence features, gray level- gradient co- occurrence features and gray level-smoothed co-occurrence features are respectively used as inputs of three types of classifiers. BP net, RBF net and a nearest neighbor classifier--K-NN method, when applying remote sensing classification for large scale panchromatic SPOT images with high spatial resolution. The result demonstrates the efficiency of the proposed algorithm.