基于分水岭与多尺度相结合的影像分割方法

广西师范大学学报（自然科学版） ›› 2012, Vol. 30 ›› Issue (1): 40-44.

基于分水岭与多尺度相结合的影像分割方法

李景文^1,2, 张紫萍^1,2, 郭伟立³, 苏浩⁴, 罗文彬⁴

1.桂林理工大学土木与建筑工程学院,广西桂林541004;
2.广西空间信息与测绘重点实验室,广西桂林541004;
3.广西第一测绘院,广西南宁530001;
4.广西科技信息网络中心,广西南宁530012

收稿日期:2011-12-10 出版日期:2012-01-20 发布日期:2018-12-03
通讯作者: 李景文(1971—),男,内蒙赤峰人,桂林理工大学教授,博士。E-mail:lijw2008@glite.edu.cn
基金资助:
国家自然科学基金资助项目(11101101);广西自然科学基金重点资助项目(2011GXNSFD018003)

A High Resolution Image Segmentation Method of a Combination ofWatershed and Multi-scale

LI Jing-wen^1,2, ZHANG Zi-ping^1,2, GUO Wei-li³, SU Hao⁴, LUO Wen-bing⁴

1.College of Civil Engineering,Guilin University of Technology,Guilin Guangxi 541004,China;
2.Guangxi Key Laboratory of Spatial Information and Geomatics,Guilin University of Technology,Guilin Guangxi 541004,China;
3.First Mapping Courtyard of Guangxi,Nanning Guangxi 530001,China;
4.Guangxi Science and Technology Information Network Center,Nanning Guangxi 530012

Received:2011-12-10 Online:2012-01-20 Published:2018-12-03

摘要/Abstract

摘要： 分水岭分割是一种应用较广泛的影像分割方法,它能自动生成单像素宽度的封闭轮廓,但需要把影像分割成过多小区域,从而导致影像分割耗时且工作量大。本文就此提出一种分水岭和多尺度相结合的高分辨率影像分割方法。该方法首先运用分水岭方法对融合了亮度梯度和纹理梯度的综合梯度进行计算,然后将同质性度量值最小的区域对合并,最后结合改进区域邻接图进行区域合并。实验结果与基于分水岭和区域合并的影像分割算法得到的结果进行比较,证明该方法不仅能充分利用高分辨率遥感影像中地物的光谱、形状、纹理等特征,而且减少了计算时间。

关键词: 影像分割, 分水岭方法, 多尺度分割, 耕地信息提取

Abstract: Watershed segmentation is a widely used automatic scheme to generate close outlines.It might give rise to closed contour of single pixel width.Using this method the image needs to be divided into many small areaswhich leads to huge workload.This paper proposes a watershed and multi-scale comprehensive image segmentation method.Firstly,calculate the comprehensive gradient which merges the brightness gradient and the texture gradient by using watershed algorithm,then,merge the area of the smallest homogeneity measure (spectral,shape and texture homogeneity metric),and the last,improve region adjacency graph.The experimental result is compared with watershed and region merging image segmentation algorithm,this method proves that it can not only take the advantageof high resolution remote sensing image features in the spectrum,shape,textureand other characteristics,and reduce the computational time.

Key words: image segmentation, watershed algorithm, multi-scalesegmentation, farmland information extraction

中图分类号:

P273

李景文, 张紫萍, 郭伟立, 苏浩, 罗文彬. 基于分水岭与多尺度相结合的影像分割方法[J]. 广西师范大学学报（自然科学版）, 2012, 30(1): 40-44.

LI Jing-wen, ZHANG Zi-ping, GUO Wei-li, SU Hao, LUO Wen-bing. A High Resolution Image Segmentation Method of a Combination ofWatershed and Multi-scale[J]. Journal of Guangxi Normal University(Natural Science Edition), 2012, 30(1): 40-44.

参考文献

[1] MEYER F.An overview of morphological segmentation[J].Inter J Pattern Recog Artif Intell,2001,15(7):1089-18.
[2] LOTUFO R,SILVA W.Mininal set of markers for the watershed transform[C]//Proceedings of ISMM 2002.Collingwood,Victoria:CSIRO Publishing,2002:359-368.
[3] GUOHONG B.B-assignment problems[J].Journal of Systems Science and Systems Engineering,1997,6(1):1-4.
[4] 刁智华,赵春江,郭新宇,等.分水岭算法的改进方法研究[J].计算机工程,2010,36(17):4-6.
[5] BLEAU A,LEON L J.Watershed-based segmentation and region merging[J].Computer Vision and Image Understanding,2000,77(3):317-370.
[6] 罗玲,解梅,陈杉.基于多尺度形态滤波的分水岭图像分割方法[J].计算机辅助设计与图形学报,2004,16(2):168-173.
[7] 陈忠.高分辨率遥感图像分类技术研究[D].北京:中国科学院遥感应用研究所,2006.
[8] 陈秋晓.高分辨率遥感图像分割方法研究[D].北京:中国科学院地理科学与资源研究所,2004.
[9] 刘海宾,何希勤,刘向东.基于分水岭和区域合并的图像分割算法[J].计算机应用研究,2007,24(9):307-308.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed