融合超像素与Wasserstein距离的遥感影像分割方法

Remote Sensing Image Segmentation Method Based on Fusion of Super Pixel and Wasserstein Distance

图像分割技术是图像处理和计算机视觉领域中的关键技术之一。随着近年来遥感成像技术的迅猛发展,传统基于像素的影像处理方法不再适用于高分辨率遥感影像。针对传统图像分割方法在分割准确性以及分割效率等问题上存在的不足,提出了一种融合超像素与Wasserstein距离的遥感影像分割方法。首先,对遥感影像进行SLIC(simple linear iterative clustering)算法预分割,生成超像素;然后,将超像素作为K-means算法的聚类中心,利用Wasserstein距离替代传统欧氏距离计算超像素之间的距离,完成聚类。理论和实验结果表明,新方法具有收敛性,在一定程度上提高了超像素预分割后的完整性,并且Wasserstein距离能够准确计算分布之间的差异性,在超像素距离计算上表现突出。

Image segmentation technology is one of the key technologies in the field of image processing and computer vision.With the rapid development of remote sensing imaging technology in recent years,the traditional pixel based image processing method is no longer suitable for high-resolution remote sensing images.Aiming at the shortcomings of traditional image segmentation methods in segmentation accuracy and efficiency,a remote sensing image segmentation method based on fusion of super-pixel and Wasserstein distance is proposed.Firstly,SLIC(simple linear iterative clustering) algorithm is used to pre segment the remote sensing image to generate super-pixel.Then,the super-pixel is used as the clustering center of K-means algorithm,and the Wasserstein distance is used to replace the traditional Euclidean distance to calculate the distance between the super-pixel and complete the clustering.Theoretical and experimental results show that the new method improves the integrity of the pre segmented super-pixel to a certain extent,and the Wasserstein distance can accurately calculate the difference between distributions,which is outstanding in the calculation of super-pixel distance.