A novel hyperspectral image classification approach based on multiresolution segmentation with a few labeled samples
A novel hyperspectral image classification approach based on multiresolution segmentation with a few labeled samples
复制标题
一种基于多分辨率分割和少量标记样本的新型高光谱图像分类方法
DOI：
10.1177/1729881417710219
复制
发表时间：
2017-05
影响因子：
2.3
通讯作者：
Yanan Wu
中科院分区：
文献类型：
--
作者：
Binge Cui;Xiudan Ma;Faxi Zhao;Yanan Wu
高光谱遥感技术是近年来发展起来的一种遥感技术，可以应用于卫星、飞机、飞行机器人等领域。高光谱遥感的一个重要应用是地面物体的分类。然而，当标记样本的数量很小时，像素分类器的分类精度会急剧下降。提出了一种基于多分辨率分割的高光谱图像分类方法。该方法的动机是一个同质区域内的像素很可能具有相同的类标签，这可以用来增加标记的样本的数量。所提出的方法包括四个步骤。首先，采用多分辨率图像分割方法对高光谱图像进行分割。其次，随机选取与标记像素位于同一区域的未标记相邻像素来分配类别标签。然后，使用一种像素级分类器，即支持向量机，对新标记样本集的高光谱图像进行分类。最后，对分类结果进行边缘保持滤波，去除椒盐噪声，保持地物边缘。在3幅真实的高光谱图像上的实验结果表明，该方法在标记样本数量较少的情况下，能够显著提高分类精度。
Hyperspectral remote sensing technology becomes more and more popular in recent years which can be applied to satellite, plane, and flying robots. An important application of hyperspectral remote sensing is the classification of ground objects. However, when the number of labeled samples is very small, the classification accuracy of pixelwise classifiers will decline dramatically. In this article, a novel hyperspectral image classification approach is proposed based on multiresolution segmentation with a few labeled samples. The proposed method is motivated by the fact that pixels within a homogenous region are very likely to have the same class label, which can be utilized to increase the number of labeled samples. The proposed method consists of four steps. First, the hyperspectral image was segmented using the multiresolution image segmentation method. Second, the unlabeled neighbor pixels in the same region as the labeled pixels were selected randomly to assign the class labels. Next, one pixelwise classifier, that is, support vector machine, is used to classify the hyperspectral image with the new labeled sample set. Finally, edge-preserving filtering is performed on the classification result to remove the salt-and-pepper noise and preserve edges of ground objects. Experimental results on three real hyperspectral images demonstrate that the proposed method can improve the classification accuracy significantly when the number of labeled samples is relatively small.
登录
查看更多内容
DOI：
--
发表时间：
2008-07
期刊：
--
影响因子：
--
作者：
Noah D. Goodman;Vikash K. Mansinghka;Daniel M. Roy;Keith Bonawitz;J. Tenenbaum
通讯作者：
Noah D. Goodman;Vikash K. Mansinghka;Daniel M. Roy;Keith Bonawitz;J. Tenenbaum
DOI：
--
发表时间：
1980
期刊：
--
影响因子：
--
作者：
Michael Brawne
通讯作者：
Michael Brawne
DOI：
10.1109/icpr.2000.903731
发表时间：
2000-09
期刊：
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
影响因子：
--
作者：
Toshio Uchiyama;N. Mukawa;H. Kaneko
通讯作者：
Toshio Uchiyama;N. Mukawa;H. Kaneko
DOI：
10.1109/34.868688
发表时间：
2000-08-01
影响因子：
23.6
作者：
Shi, JB;Malik, J
通讯作者：
Malik, J
影响因子：
10.6
作者：
Petrovic, A;Escoda, OD;Vandergheynst, P
通讯作者：
Vandergheynst, P