Integrating Color Features in Polarimetric SAR Image Classification
Integrating Color Features in Polarimetric SAR Image Classification
复制标题
DOI：
10.1109/tgrs.2013.2258675
复制
发表时间：
2014-04-01
影响因子：
8.2
通讯作者：
Kiranyaz, Serkan
中科院分区：
文献类型：
--
作者：
Uhlmann, Stefan;Kiranyaz, Serkan
极化合成孔径雷达（PolSAR）数据广泛应用于地形分类，利用各种目标分解的SAR特征和某些纹理特征。然而，PolSAR分类中有一个信息来源迄今为止一直被忽视：颜色。通过颜色编码方法将PolSAR数据可视化是一种常见的做法，因此可以从这些伪彩色图像中提取强大的颜色特征，从而为更好的地形分类提供额外的数据。在本文中，我们首先回顾了以往使用各种特征组合进行PolSAR分类的尝试，然后介绍并深入研究了除了SAR和纹理特征之外，Pauli颜色编码图像上颜色特征的应用。我们对来自RADARSAT-2和AIRSAR系统分别在C波段和l波段工作的弗莱弗兰和旧金山湾地区的三幅图像进行了广泛的比较评估，使用了24种不同的特征集组合。然后，我们考虑支持向量机和随机森林分类器拓扑来测试和评估颜色特征对分类性能的作用。分类结果表明，在土地利用和土地覆盖分类应用中，与传统使用的PolSAR和纹理特征相比，额外的颜色特征引入了一个新的识别水平，并在分类性能上有了显著提高。
Polarimetric synthetic aperture radar (PolSAR) data are used extensively for terrain classification applying SAR features from various target decompositions and certain textural features. However, one source of information has so far been neglected from PolSAR classification: Color. It is a common practice to visualize PolSAR data by color coding methods and thus, it is possible to extract powerful color features from such pseudocolor images so as to provide additional data for a superior terrain classification. In this paper, we first review previous attempts for PolSAR classifications using various feature combinations and then we introduce and perform in-depth investigation of the application of color features over the Pauli color-coded images besides SAR and texture features. We run an extensive set of comparative evaluations using 24 different feature set combinations over three images of the Flevoland- and the San Francisco Bay region from the RADARSAT-2 and the AIRSAR systems operating in C- and L-bands, respectively. We then consider support vector machines and random forests classifier topologies to test and evaluate the role of color features over the classification performance. The classification results show that the additional color features introduce a new level of discrimination and provide noteworthy improvement in classification performance (compared with the traditionally employed PolSAR and texture features) within the application of land use and land cover classification.