基于非负矩阵分解和支持向量机的墨西哥湾溢油HJ-1星遥感图像分类

为提高国产自主卫星在海洋溢油监测中的精度,提出一种基于非负矩阵分解和支持向量机的环境减灾星(HJ-1)海洋溢油遥感图像分类算法。针对HJ-1星遥感图像,首先利用非负矩阵分解算法进行图像特征提取,相对图像光谱和纹理等图像基本特征,构造具有针对性的溢油图像局部化非负特征,更符合遥感图像特征所对应的物理意义。进而在新特征的基础上,采用支持向量机实现遥感图像分类,解决小样本训练问题。通过墨西哥湾溢油遥感图像仿真实验比较,证明该方法在HJ-1星溢油图像分类中的有效性。

HJ-1 satellite remote sensing image segmentation in the oil spill of Mexico Gulf base on the non-negative matrix factorization and support vector machine

To improve self-made satellites in the marine oil spill monitoring accuracy,it is presented that an environmental mitigation satellite (HJ-1) marine oil spill remote sensing image classification algorithm based on non-negative matrix factorization and support vector machine algorithm.Focusing on remote sensing images of HJ-1 satellite,a non-negative matrix factorization algorithm is adopted to extract the image features.Compared with basic features,such as the image spectrum and texture,structuring more targeted oil spill image localization non-negative character fits better for the physical significance of remote sensing images.Furthermore,based on the new features,the support vector machine is employed for remote sensing image classification.It remedies the problem of small sample training.Simulation results of the Gulf of Mexico oil spill event substantiate the effectiveness of the proposed approach for HJ-1 satellite image classification.