Hybrid region merging method for segmentation of high-resolution remote sensing images
Hybrid region merging method for segmentation of high-resolution remote sensing images
复制标题
DOI：
10.1016/j.isprsjprs.2014.09.011
复制
发表时间：
2014-12
影响因子：
12.7
通讯作者：
Xue-liang Zhang;P. Xiao;Xuezhi Feng;Jiangeng Wang;Zuo Wang
中科院分区：
文献类型：
--
作者：
Xue-liang Zhang;P. Xiao;Xuezhi Feng;Jiangeng Wang;Zuo Wang
图像分割是基于对象的图像分析中的一个具有挑战性的问题。本文提出了一种混合区域合并（HRM）方法来分割高分辨率遥感图像。人力资源管理整合了面向全球和面向本地的区域合并战略的优势，成为一个统一的框架。该算法利用全局最相似区域对确定生长区域的起始点，避免了起始点分配问题，提高了局部区域合并的优化能力.在区域生长过程中，合并迭代被限制在局部邻域内，从而与面向全局的方法相比，分割速度更快，并且可以反映局部上下文。采用一组高分辨率遥感影像对HRM方法的有效性进行了测试，并采用eCognition Developer软件中嵌入的分层逐步优化（HSWO）方法、局部互最佳区域合并（LMM）方法和多分辨率分割（MRS）方法进行了比较。监督评估和视觉评估都表明，HRM的表现优于HSWO和LMM结合两者的优点。HRM和MRS的分割结果在视觉上具有可比性，但HRM比MRS更能将对象描述为单个区域，监督和非监督评价结果进一步证明了HRM的优越性。
Image segmentation remains a challenging problem for object-based image analysis. In this paper, a hybrid region merging (HRM) method is proposed to segment high-resolution remote sensing images. HRM integrates the advantages of global-oriented and local-oriented region merging strategies into a unified framework. The globally most-similar pair of regions is used to determine the starting point of a growing region, which provides an elegant way to avoid the problem of starting point assignment and to enhance the optimization ability for local-oriented region merging. During the region growing procedure, the merging iterations are constrained within the local vicinity, so that the segmentation is accelerated and can reflect the local context, as compared with the global-oriented method. A set of high-resolution remote sensing images is used to test the effectiveness of the HRM method, and three region-based remote sensing image segmentation methods are adopted for comparison, including the hierarchical stepwise optimization (HSWO) method, the local-mutual best region merging (LMM) method, and the multiresolution segmentation (MRS) method embedded in eCognition Developer software. Both the supervised evaluation and visual assessment show that HRM performs better than HSWO and LMM by combining both their advantages. The segmentation results of HRM and MRS are visually comparable, but HRM can describe objects as single regions better than MRS, and the supervised and unsupervised evaluation results further prove the superiority of HRM.