基于自适应主动学习与联合双边滤波的高光谱图像分类

Hyperspectral Image Classification Based on Adaptive Active Learning and Joint Bilateral Filtering

在高光谱图像分类中,选择合适的样本作为训练样本对分类器进行训练非常重要。将样本的不确定性与代表性相结合,通过自适应主动学习方法来完成样本的选择。用核K均值聚类来获取具有代表性的样本,用最优标号和次优标号的概率差值与两者比值的加权和来度量不确定性。此外,为了提高分类的准确率,利用联合双边滤波来获取高光谱图像的空间信息,并将其融入分类过程中。最后,提出一种融合自适应主动学习与联合双边滤波的空谱结合高光谱图像分类方法,并通过实验验证了所提方法的优越性。

It is very important to select appropriate samples as training samples to train the classifier in hyperspectral image classification(HIC).In this paper,the uncertainty and representativeness of the sample are combined,and the sample selection is completed by the adaptive active learning method.The Kernel-K clustering means is used to obtain representative samples,while the uncertainty is determined by the weighted sum of the probability difference between the optimal label and the suboptimal label and their ratio.In addition,in order to improve the accuracy of classification,the joint bilateral filtering is used to obtain the spatial information of hyperspectral image,and it is incorporated into the classification process.Finally,a spatial-spectral HIC approach is proposed,which combines adaptive active learning and joint bilateral filtering.The experimental results show the superiority of the proposed method.