[1]李士进,王声特.基于混合特征空间MRF(Markov Random Filed)模型的高分辨率遥感影像水体提取[J].南京师范大学学报(自然科学版),2017,40(01):13.[doi:10.3969/j.issn.1001-4616.2017.01.003]
　Li Shijin,Wang Shengte.A New Algorithm Based on Hybrid Feature Space MRF(MarkovRandom Filed)Model for Water Information Extractionfrom High Resolution Remote Sensing Imagery[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(01):13.[doi:10.3969/j.issn.1001-4616.2017.01.003]
点击复制

基于混合特征空间MRF(Markov Random Filed)模型的高分辨率遥感影像水体提取()
分享到：

《南京师范大学学报》（自然科学版）[ISSN:1001-4616/CN:32-1239/N]

卷:
第40卷
期数:
2017年01期
页码:
13
栏目:
·数学与计算机科学·
出版日期:
2017-03-31

文章信息/Info

Title:
A New Algorithm Based on Hybrid Feature Space MRF(MarkovRandom Filed)Model for Water Information Extractionfrom High Resolution Remote Sensing Imagery
文章编号:
1001-4616(2017)01-0013-07
作者:
李士进; 王声特
河海大学计算机与信息学院,江苏 南京 210098
Author(s):
Li Shijin; Wang Shengte
College of Computer and Information,Hohai University,Nanjing 210098,China
关键词:
水体提取; MRF模型; 归一化差异水体指数(NDWI); 混合特征; 图割算法(Graph Cut)
Keywords:
water body extraction; MRF model; normalized difference water index(NDWI); hybrid feature space; Graph Cut
分类号:
TP753
DOI:
10.3969/j.issn.1001-4616.2017.01.003
文献标志码:
A
摘要:
水体信息提取是遥感图像在水资源调查与利用、水生态监测等应用中的关键技术之一. 针对现有的水体指数法或影像分类法在水体边界处理效果不够精确、易产生误提取和漏提取等问题,提出一种基于混合特征空间与MRF模型图像分割算法的水体提取新算法. 结合遥感图像颜色特征与归一化差异水体指数NDWI创建混合特征空间,将遥感图像中的像素作为MRF模型中的随机变量,构建基于混合特征的能量函数,使用迭代的图割算法(Graph Cut)最小化能量函数确定水体边界,然后根据已提取的水体主体的水体指数及颜色特征等信息对水体边界进行自适应精细化处理. 对石梁河水库水体提取的实验表明,该方法能够自动对周边环境复杂的水库水体信息进行提取,并且水体边界的提取效果良好,达到较高的水体提取精度.
Abstract:
Water information extraction in remote sensing images is an important application of remote sensing technology in water resources surveying and utilization,detection of water ecology change and other aspects. The existing water extraction methods as water index or image classification are not accurate enough for water boundary treatment,and they are easy to produce the problem of error extraction and leakage extraction. Based on the existing algorithms that constructing water index to extract water information,we have proposed a new algorithm which combine image segmentation algorithm based on MRF model with normalized difference water index(NDWI)for extraction of water information. We represent the pixels in a remote sensing image as random variables in an MRF model,and introduce hybrid feature in the energy function on these variables,minimize the energy function to find the optimal water boundary,by using an iterative graph cut scheme. Then water boundary is adaptively refined according to the water index and color feature of the extracted water body. The experiment of water information extraction in Shilianghe Reservoir shows that our approach can achieve significant accuracy as it automatically adapts to the extraction of water information in reservoir whose surroundings are complicated and the boundary of water bodies is handled precisely.

参考文献/References:

[1] 胡晓东,骆剑承,夏列钢,等. 图谱迭代反馈的自适应水体信息提取方法[J]. 测绘学报,2011,40(5):544-550.
[2]骆剑承,盛永伟,沈占锋,等. 分步迭代的多光谱遥感水体信息高精度自动提取[J]. 遥感学报,2009,13(4):610-615.
[3]沈占锋,夏列钢,李均力,等. 采用高斯归一化水体指数实现遥感影像河流的精确提取[J]. 中国图象图形学报,2013,18(4):421-428.
[4]王华. 基于 VWRD 的遥感影像面状居民地和水体提取[D]. 武汉:武汉大学,2010.
[5]FRAZIER P S,PAGE K J. Water body detection and delineation with Landsat TM data[J]. Photogrammetric engineering and remote sensing,2000,66(12):1 461-1 468.
[6]MCFEETERS S K. The use of normalized difference water index(NDWI)in the delineation of open water features[J]. International journal of remote sensing,1996,17(7):1 425-1 432.
[7]徐涵秋. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J]. 遥感学报,2005,9(5):589-595.
[8]周艺,谢光磊,王世新,等. 利用伪归一化差异水体指数提取城镇周边细小河流信息[J]. 地球信息科学学报,2014,16(1):102-107.
[9]陈文倩,丁建丽,李艳华,等. 基于国产GF-1遥感影像的水体提取方法[J]. 资源科学,2015,37(6):1 166-1 172.
[10]吉红霞,范兴旺,吴桂平,等. 离散型湖泊水体提取方法精度对比分析[J]. 湖泊科学,2015,27(2):327-334.
[11]陈亮,张友静,何厚军,等. 基于混合像元分解的水体面积提取算法[J]. 河海大学学报(自然科学版),2014,42(4):346-350.
[12]BOYKOV Y Y,JOLLY M P. Interactive graph cuts for optimal boundary & region segmentation of objects in ND images[C]//2001 IEEE International Conference on Computer Vision(ICCV). Vancouver,Canada:IEEE,2001:105-112.
[13]朱利,李云梅,赵少华,等. 基于GF-1号卫星WFV数据的太湖水质遥感监测[J]. 国土资源遥感,2015,27(1):113-120.
[14]MISHRA A,ALAHARI K,JAWAHAR C V. An MRF model for binarization of natural scene text[C]//2011 International Conference on Document Analysis and Recognition(ICDAR). Beijing,China:IEEE,2011:11-16.
[15]刘磊,石志国,宿浩茹,等. 基于高阶马尔可夫随机场的图像分割[J]. 计算机研究与发展,2013,50(9):1 933-1 942.
[16]ROTHER C,KOLMOGOROV V,BLAKE A. Grabcut:interactive foreground extraction using iterated graph cuts[J]. ACM transactions on graphics(TOG),2004,23(3):309-314.
[17]BOYKOV Y,KOLMOGOROV V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE transactions on pattern analysis and machine intelligence,2004,26(9):1 124-1 137.

备注/Memo

备注/Memo:
收稿日期:2016-05-14.
基金项目:国家自然科学基金(61170200)、江苏省重点研发计划(社会发展)项目(BE2015707).
通讯联系人:李士进,博士,教授,研究方向:模式识别和数据挖掘. E-mail:lishijin@hhu.edu.cn
更新日期/Last Update: 1900-01-01