Optimal Segmentation of High-Resolution Remote Sensing Image by Combining Superpixels With the Minimum Spanning Tree
Optimal Segmentation of High-Resolution Remote Sensing Image by Combining Superpixels With the Minimum Spanning Tree
复制标题
超像素与最小生成树相结合的高分辨率遥感图像优化分割
DOI：
10.1109/tgrs.2017.2745507
复制
发表时间：
2018-01-01
影响因子：
8.2
通讯作者：
Li, Deren
中科院分区：
文献类型：
--
作者：
Wang, Mi;Dong, Zhipeng;Li, Deren
图像分割是基于对象的图像分析的基础，许多研究人员都在寻求最佳的分割结果。初始图像过分割和最优分割尺度是高空间分辨率遥感图像分割的两个重要因素。针对这两个问题，本文提出了一种结合超像素和最小生成树的图像分割方法。首先，使用简单的线性迭代聚类算法对图像进行过分割以获得超像素。然后，利用初始分段数，采用动态约束凝聚聚类和分区（REDCAP）算法对超像素进行区域化聚类，得到与分段数对应的局部方差（LV）和LV变化率（ROC-LV）指标图。根据分段数对应的LV和ROC-LV指标图确定合适的图像分段数。最后，根据合适的图像分割数，利用REDCAP算法对超像素进行重新聚类，得到图像分割结果。通过两组实验，将所提出的方法与其他两种分割算法进行了比较。实验结果表明，该方法优于其他方法，取得了良好的图像分割效果。
Image segmentation is the foundation of object-based image analysis, and many researchers have sought optimal segmentation results. The initial image oversegmentation and the optimal segmentation scale are two vital factors in high spatial resolution remote sensing image segmentation. With respect to these two issues, a novel image segmentation method combining superpixels with a minimum spanning tree is proposed in this paper. First, the image is oversegmented using a simple linear iterative clustering algorithm to obtain superpixels. Then, the superpixels are clustered by regionalization with a dynamically constrained agglomerative clustering and partitioning (REDCAP) algorithm using the initial number of segments, and the local variance (LV) and the rate of LV change (ROC-LV) indicator diagrams corresponding to the number of segments are obtained. The suitable number of image segments is determined according to the LV and ROC-LV indicator diagrams corresponding to the number of segments. Finally, the superpixels are reclustered using the REDCAP algorithm based on the suitable number of image segments to obtain the image segmentation result. Through two sets of experiments, the proposed method is compared with two other segmentation algorithms. The experimental results show that the proposed method outperforms the others and obtains good image segmentation results.