摘要
提出了一种融合像元-多尺度对象级特征的高分辨率遥感影像道路中心线提取方法。首先在像素级上提取影像的纹理和形状结构特征,在构建的多尺度分割集影像上提取对象的区域光谱特征。然后,将像元级特征与多尺度对象特征进行决策级融合,完成道路网的粗提取。最后,结合本文所提出的非道路区域自动去除算法和张量投票算法,实现道路中心线的精提取。不同场景、不同分辨率数据下开展的试验结果表明,该方法可有效改善传统道路提取方法易产生的"盐噪声"和非道路地物粘连现象。
A novel approach for road centerline extraction from high spatial resolution satellite imagery is proposed by fusing both pixel-based and object-based features.Firstly,texture and shape features are extracted at the pixel level,and spectral features are extracted at the object level based on multi-scale image segmentation maps.Then,extracted multiple features are utilized in the fusion framework of Dempster-Shafer evidence theory to roughly identify the road network regions.Finally,an automatic noise removing algorithm combined with the tensor voting strategy is presented to accurately extract the road centerline.Experimental results using high-resolution satellite imageries with different scenes and spatial resolutions showed that the proposed approach compared favorably with the traditional methods,particularly in the aspect of eliminating the salt noise and conglutination phenomenon.
作者
曹云刚
王志盼
慎利
肖雪
杨磊
CAO Yungang WANG Zhipan SHEN Li XIAO Xue YANG Lei(State-province Joint Engineering Laboratory of Spatial Information Technology of High-speed Railway Safety, Southwest Jiaotong University, Chengdu 611756, China Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University, Chengdu 611756, China Sichuan Province Second Geographic Information Engineering Institute of Surveying and Mapping, Chengdu 610100, China)
出处
《测绘学报》
EI
CSCD
北大核心
2016年第10期1231-1240,1249,共11页
Acta Geodaetica et Cartographica Sinica
基金
国家重点基础研究计划(2012CB719901)
国家自然科学基金(41201434
41401374)
数字制图与国土信息应用工程国家测绘地理信息局重点实验室开放基金(DM2016SC06)
四川省地理国情监测工程技术研究中心开放基金(GC201516)~~
关键词
高分辨率遥感
多特征融合
道路提取
基于像素
面向对象
high resolution remote sensing
multiple feature fusion
road extraction
pixel-based
object-based
作者简介
第一作者简介：曹云刚（1978-），男，副教授，研究方向为资源与环境遥感。E-mail：yungang@swjtu．cn
通信作者：慎利E-mail：rsshenli@outlook．com
