一种基于概率框架的遥感影像分割方法

doi:10.13474/j.cnki.11-2246.2018.0102

测绘通报 ›› 2018, Vol. 0 ›› Issue (4): 10-15.doi: 10.13474/j.cnki.11-2246.2018.0102

一种基于概率框架的遥感影像分割方法

赵展, 闫利, 夏旺

武汉大学测绘学院, 湖北武汉 430079

收稿日期:2017-07-17 出版日期:2018-04-25 发布日期:2018-05-03
作者简介:赵展(1984-),男,博士,讲师,主要从事遥感影像分割、分类等方面研究。E-mail:zhzhao@sgg.whu.edu.cn
基金资助:
国土资源部公益性行业科研专项经费（201511009）

A Probabilistic Framework for the Segmentation of Remote Sensing Imagery

ZHAO Zhan, YAN Li, XIA Wang

School of Geodsy and Geomatics, Wuhan University, Wuhan 430079, China

Received:2017-07-17 Online:2018-04-25 Published:2018-05-03

摘要/Abstract

摘要：

基于区域增长的影像分割方法存在着种子选择和分割参数设置的难点。针对这两点，本文提出了一种基于概率合并框架的高分辨率遥感影像分割方法。首先，利用基于标记的分水岭变换和区域合并获得一个初始分割结果，避开种子点的选择；其次，利用初始分割所获得的具有一定大小的区域，计算统计、上下文和形状特征信息；然后，在贝叶斯准则的基础上，计算一个尺度无关的相邻区域间的合并概率，其应用于区域增长合并过程，合并概率具有直观统计意义，可以减少阈值确定的难度；同时由于区域的合并概率具有尺度无关性，可以在一次分割中成功地分割出不同尺度的地物；最后进行了试验，通过目视和定量分析及与eCognition分割结果的对比证明了本文算法的有效性。

关键词: 遥感影像分割, 概率框架, 区域增长, 分水岭变换

Abstract:

Image segmentation method based on region growing suffers the problem of selecting appropriate growing seeds and segmentation parameters.A segmentation method based on a novel kind of region-merging probability measure is proposed to solve the problem in this paper.First,an initial segmentation is achieved by marker-based watershed transformation and simple region merging.Statistic,context and shape information can be calculated from the initial segmentation regions.Then a scale-independent merging probability of neighboring regions is calculated by the information based on Bayesian criterion,which is integrated into sequential region merging procedure.It is easier to determine a threshold value for the new probability measure because of its intuitive meaning.And multi-scale objects can be simultaneously segmented in once segmentation,since the probability is independent of scale.Experiment shows a good performance of the method by visual and quantitative analysis and compared with multi-resolution segmentation results of eCognition.

Key words: remote sensing image segmentation, probabilistic framework, regional growth, watershed transformation

中图分类号:

P237

赵展, 闫利, 夏旺. 一种基于概率框架的遥感影像分割方法[J]. 测绘通报, 2018, 0(4): 10-15.

ZHAO Zhan, YAN Li, XIA Wang. A Probabilistic Framework for the Segmentation of Remote Sensing Imagery[J]. 测绘通报, 2018, 0(4): 10-15.

参考文献

[1] BENZ U C,HOFMANN P,WILLHAUCK G,et al.Multi-resolution,Object-oriented Fuzzy Analysis of Remote Sensing Data for GIS-ready Information[J].ISPRS Journal of Photogrammetry & Remote Sensing,2004,58(3):239-258.
[2] 赵泉华,常波,王玉,等.结合模糊分割和遗传算法的航空影像车辆提取方法[J].测绘通报,2017(8):62-66.
[3] WOODCOCK C,HARWARD V J.Nested-hierarchical Scene Models and Image Segmentation[J].International Journal of Remote Sensing,1992,13(16):3167-3187.
[4] BAATZ M,SCHÄPE A.An Optimization Approach for High Quality Multi-scale Image Segmentation[C]//Beiträge Zum AGIT-Symposium.[S.l.]:AGIT,2000:12-23.
[5] NOCK R,NIELSEN F.Statistical Region Merging[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2004,26(11):1452-1458.
[6] BYUN Y,KIM D,LEE J,et al.A Framework for the Segmentation of High-resolution Satellite Imagery Using Modified Seeded-region Growing and Region Merging[J].International Journal of Remote Sensing,2011,32(16):4589-4609.
[7] CASTILLA G,HAY G J,RUIZ J R.Size-constrained Region Merging (SCRM):An Automated Delineation Tool for Assisted Photointerpretation[J].Photogrammetric Engineering & Remote Sensing,2008,74(4):409-419.
[8] SANZ T R,STAMON G,LOUCHET J.Using Colour,Texture,and Hierarchial Segmentation for High-resolution Remote Sensing[J].ISPRS Journal of Photogrammetry & Remote Sensing,2008,63(2):156-168.
[9] CHEN Z,ZHAO Z,GONG P,et al.A New Process for the Segmentation of High Resolution Remote Sensing Imagery[J].International Journal of Remote Sensing,2006,27(22):4991-5001.
[10] CHEN Zhong,WANG Guoyou,LIU Jianguo.A Modified Object-oriented Classification Algorithm and Its Application in High-resolution Remote-sensing Imagery[J].International Journal of Remote Sensing,2012,33(10):3048-3062.
[11] LI H,GU H,HAN Y,et al.An Efficient Multiscale SRMMHR (Statistical Region Merging and Minimum Heterogeneity Rule) Segmentation Method for High-resolution Remote Sensing Imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2009,2(2):67-73.
[12] WANG L,GONG P,YING Q,et al.Settlement Extraction in the North China Plain Using Landsat and Beijing-1 Multispectral Data with an Improved Watershed Segmentation Algorithm[J].International Journal of Remote Sensing,2010,31(6):1411-1426.
[13] YI L,ZHANG G,WU Z.A Scale-synthesis Method for High Spatial Resolution Remote Sensing Image Segmentation[J].IEEE Transactions on Geoscience & Remote Sensing,2012,50(10):4062-4070.
[14] ZHONG Y,ZHAO B,ZHANG L.Multiagent Object-based Classifier for High Spatial Resolution Imagery[J].IEEE Transactions on Geoscience & Remote Sensing,2013,52(2):841-857.
[15] HU Z,LI Q,ZOU Q,et al.A Bilevel Scale-sets Model for Hierarchical Representation of Large Remote Sensing Images[J].IEEE Transactions on Geoscience & Remote Sensing,2016,54(12):7366-7377.
[16] 刘婧,李培军.结合结构和光谱特征的高分辨率影像分割方法[J].测绘学报,2014,43(5):466-473.
[17] 肖鹏峰,冯学智,赵书河,等.基于相位一致的高分辨率遥感图像分割方法[J].测绘学报,2007,36(2):146-151.
[18] LI D,ZHANG G,WU Z,et al.An Edge Embedded Marker-based Watershed Algorithm for High Spatial Resolution Remote Sensing Image Segmentation[J].IEEE Transactions on Image Processing,2010,19(10):2781-2787.
[19] 巫兆聪,胡忠文,欧阳群东.一种区域自适应的遥感影像分水岭分割算法[J].武汉大学学报(信息科学版),2011,36(3):293-296.
[20] LI P,GUO J,SONG B,et al.A Multilevel Hierarchical Image Segmentation Method for Urban Impervious Surface Mapping Using Very High Resolution Imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2011,4(1):103-116.
[21] ALPERT S,GALUN M,BASRI R,et al.Image Segmentation by Probabilistic Bottom-up Aggregation and Cue Integration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):315-327.
[22] MING D,CI T,CAI H,et al.Semivariogram-based Spatial Bandwidth Selection for Remote Sensing Image Segmentation with Mean-shift Algorithm[J].IEEE Geoscience & Remote Sensing Letters,2012,9(5):813-817.

一种基于概率框架的遥感影像分割方法

A Probabilistic Framework for the Segmentation of Remote Sensing Imagery

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	冯朝晖, 李芹, 韩留生, 薛国超, 赵红颖. 改进分水岭方法下的遥感图像水体提取[J]. 测绘通报, 2019, 0(6): 11-15.
[2]	贺亦峰, 胡荣, 邹进贵. 利用三维激光扫描数据进行建筑物立面点云分割算法分析[J]. 测绘通报, 2019, 0(4): 26-31.
[3]	李莹, 苏国中, 林宗坚. 倾斜影像中提取高精度DEM的方法研究[J]. 测绘通报, 2017, 0(2): 30-34.
[4]	赵传, 张保明, 陈小卫, 郭海涛, 唐梁珂. 一种基于LiDAR点云的建筑物提取方法[J]. 测绘通报, 2017, 0(2): 35-39.
[5]	于海洋余鹏磊谢秋平李宁卢小平. 机载LiDAR数据建筑物顶面点云分割方法研究[J]. 测绘通报, 2014, 0(6): 20-23.