Multi-feature Fusion for PolSAR Image Classification of Oil Slick Thickness

被引：0

作者：

Hong, Shiyi ^{[1
]}

Guo, Hao ^{[1
]}

An, Jubai ^{[1
]}

机构：

[1] Dalian Maritime Univ, Dalian 116026, Peoples R China

来源：

PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON EDUCATION, MANAGEMENT, INFORMATION AND COMPUTER SCIENCE (ICEMC 2017) | 2017年 / 73卷

基金：

中国国家自然科学基金;

关键词：

Polarimetric Synthetic Aperture Radar (PolSAR); Multi-feature fusion; Oil slick; Image classification; SAR;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The oil slick outline and the information of thickness are important indicators of estimating oil spill. How to estimate the oil slick thickness quickly is a hot research topic. In this paper, multi-feature fusion strategy is used to design classifier based on the potential correlation between Polarimetric Synthetic Aperture Radar (PolSAR) characteristics and oil slick thickness. Taking into account the correlation between polarization characteristics, Mahalanobis distance is used to optimize initial cluster center of fuzzy C-means clustering and then, the estimation of oil slick thickness is carried out. The algorithm is proved to be effective by classifying the oil slick thickness of two groups of PolSAR oil spill data in Mexico Bay.

引用

页码：220 / 223

页数：4