一种结合超像素和图论的高空间分辨率遥感影像分割方法  

A high resolution remote sensing image segmentation method based on superpixel and graph theory

作　　者：姚丙秀 黄亮[1,2] 许艳松 YAO Bingxiu;HUANG Liang;XU Yansong(Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093,China;Surveying and Mapping Geo-Informatics Technology Research Center on PlateauMountains of Yunnan Higher Education, Kunming 650093, China)

机构地区：[1]昆明理工大学国土资源工程学院,昆明650093 [2]云南省高校高原山区空间信息测绘技术应用工程研究中心,昆明650093

出　　处：《国土资源遥感》2019年第3期72-79,共8页Remote Sensing for Land & Resources

基　　金：云南省应用基础研究计划面上项目“基于全卷积神经网络的多源遥感影像变化检测”(编号:2018FB078);云南省教育厅科学研究基金资助性项目“基于模糊理论的遥感影像变化检测理论与方法研究”(编号:2016ZZX051);云南省高校工程中心建设计划、昆明理工大学引进人才科研启动基金项目“异源异构遥感影像变化检测方法研究”(编号:KKSY201521040);昆明理工大学国土资源工程学院教育教学改革项目“多学科交叉背景下测绘工程专业人才培养新模式探索”(编号:JG201804);自然资源部地球观测与时空信息科学重点实验室经费资助项目“基于直觉模糊集理论的多源遥感影像变化检测方法研究”(编号:201911)共同资助

摘　　要：超像素分割已成为遥感影像预处理研究的新热点,但易形成过分割。为解决该问题,提出一种结合超像素和图论的高空间分辨率遥感影像分割方法。首先,采用简单线性迭代聚类(simple linear iterative clustering,SLIC)算法对遥感影像生成超像素过分割影像;然后,采用图论算法对超像素进行合并,通过计算得到每次合并后的分割数对应的局部方差,确定合适的影像分割数;最后,根据合适的影像分割数用图论算法对超像素重新聚类合并。实验数据为4幅不同空间分辨率、不同场景的遥感影像,采用定性和定量相结合的方法评价实验结果。实验结果表明,该方法能有效地解决遥感影像过分割结果的问题,获得了良好的分割结果。Superpixel segmentation has become a new hotspot in remote sensing image preprocessing, but it has the problem of over segmentation. To solve this problem, the authors propose a high resolution remote sensing image segmentation method combining superpixel and graph theory. First, the simple linear iterative clustering (SLIC) algorithm is used to divide the image into superpixels, then the superpixels are merged by the graph theory algorithm, the local variance corresponding to the combined number of the merged numbers are calculated, and the appropriate image segmentation number is determined. Finally, according to the appropriate image segmentation number, the graph theory algorithm is used to recluster and merge the superpixels. Four groups of remote sensing images of different scenes and different spatial resolutions were selected as experimental data. The qualitative and quantitative analysis of experimental results was evaluated. Experimental results show that the proposed method can effectively overcome the effect of over segmentation results and achieve good segmentation results.

关 键 词：高空间分辨率遥感影像 超像素 影像分割 简单线性迭代聚类 图论 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]