High-resolution remote sensing image segmentation based on improved RIU-LBP and SRM
High-resolution remote sensing image segmentation based on improved RIU-LBP and SRM
复制标题
基于改进RIU-LBP和SRM的高分辨率遥感图像分割
DOI：
10.1186/1687-1499-2013-263
复制
发表时间：
2013-11-11
影响因子：
2.6
通讯作者：
Liu, Haijun
中科院分区：
文献类型：
--
作者：
Cheng, Jian;Li, Lan;Liu, Haijun
本文提出了一种改进的旋转不变均匀局部二值模式(RIU-LBP)算子用于高分辨率遥感图像分割，能够有效地描述高分辨率遥感图像的纹理特征。改进的RIU-LBP是在RIU-LBP的基础上提出的。它在区域像素的二值化中引入了一个阈值。与原RIU-LBP算子相比，新的LBP算子能够更好地容忍微小的纹理变化，更好地区分平纹和粗糙纹理。然后，提出了一种基于区域LBP值分布和Bhattacharyya距离的纹理区域合并准则。最后，在基于统计区域合并(SRM)的遥感图像分割方法中，充分利用高分辨率遥感图像丰富的光谱和纹理信息，将纹理合并准则和光谱合并准则相结合，提高了分割效果。该算法可以根据分割区域的数量进行调整，实验表明分割效果优于ENVI5.0和SRM方法。
In this paper, we propose an improved rotation invariant uniform local binary pattern (RIU-LBP) operator for segmenting high-resolution sensing image which can effectively describe the texture features of a high-resolution remote sensing image. The improved RIU-LBP is based on RIU-LBP. It introduces a threshold in binarization of region pixels. The new LBP operator can better tolerate small texture variation and better distinguish the plain and rough texture than the original RIU-LBP does. Then, a merging criterion of texture regions is proposed, which is based on regional LBP value distribution and Bhattacharyya distance. Finally, the texture merging criterion and spectral merging criterion are combined in the statistical region merging (SRM)-based remote sensing image segmentation method to improve segmentation results, taking full advantage of rich spectral and texture information in high-resolution remote sensing images. This algorithm can be adjusted to the number of segmented regions, and experiments indicate better segmentation results than ENVI 5.0 and the SRM method.