基于云模型、图论和互信息的遥感影像分割方法

doi:10.3969/j.issn.0372-2112.2015.08.008

电子学报 ›› 2015, Vol. 43 ›› Issue (8): 1518-1525.DOI: 10.3969/j.issn.0372-2112.2015.08.008

基于云模型、图论和互信息的遥感影像分割方法

宋岚^1,2,3, 文堂柳^1,3, 黎海生², 王杉²

1. 武汉大学软件工程国家重点实验室, 武汉大学计算机学院, 湖北武汉 430072;
2. 华东交通大学信息工程学院, 江西南昌 330013;
3. 江西师范大学高性能计算中心, 江西南昌 330022

收稿日期:2014-08-25 修回日期:2015-01-23 出版日期:2015-08-25 发布日期:2015-08-25
作者简介:宋岚 女,1978年生,江西南昌人.博士研究生,CCF会员.研究方向为无线传感器网络,图像处理,软件的形式化方法. E-mail:sl130com@gmail.com.文堂柳男,1980年生,江西赣州人.博士研究生,CCF会员.研究方向为软件的形式化方法,图像处理.黎海生男,1974年生,江西南昌人,博士,研究方向为量子图像处理,量子计算.王杉男,1981年生,江西南昌人,博士,研究方向为图像处理,细胞识别,神经网络算法等.
基金资助:
国家自然科学基金(No.61462026,No.61261041,No.61272075,No.61462041)

Segmentation Method for Remote Sensing Image Based on Cloud Model, Graph Theory and Mutual Information

SONG Lan^1,2,3, WEN Tang-liu^1,3, LI Hai-sheng², WANG Shan²

1. State Key Laboratory of Software Engineering, School of Computer, Wuhan University, Wuhan, Hubei 430072, China;
2. School of Information Engineering, East China Jiaotong University, Nanchang, Jiangxi 330013, China;
3. Key Laboratory of High Performance Computing, Jiangxi Normal University, Nanchang, Jiangxi 330022, China

Received:2014-08-25 Revised:2015-01-23 Online:2015-08-25 Published:2015-08-25

摘要/Abstract

摘要：

针对传统的基于局部信息搜索的分割方法很少考虑图像的全局信息,而且容易忽略影像分割中的随机性和不确定性,本文提出了一种基于云模型、图论和互信息的影像分割方法.使用云模型来反映像素聚类成区域时的不确定性和随机性,将图论方法引入基于互信息的最优割集的生成从而得到全局最优分割,利用云模型区域概念所呈现出的多维特征,通过云综合异质性度量来改进边界权重的计算,从而实现对区域相异性的区分能力.从实验结果来看,本文提出的方法,能产生有意义的、完整的、内部同质的分割区域,在分割精度上基本能满足人眼的视觉要求.

关键词: 云模型, 小波降噪, Harris算子, 互信息, 图论, 最小生成树

Abstract:

The traditional segmentation method which is based on local information search technique gives little regard for the global information of the image and ignores the randomness and uncertainty of image segmentation.In view of this, this paper proposes a new segmentation method which is based on cloud model, graph theory and mutual information.Firstly, we could use the cloud model to reflect the uncertainty and randomness when pixel cluster into regions.Secondly, when the graph theory method is introduced into a quasi-optimal cut sets, we could obtain a globally optimal segmentation.Thirdly, by using the multidimensional characteristics which are showed by regional concept of cloud model, we could use a comprehensive heterogeneity measure to improve border weights, and therefore improve the ability to distinguish regional dissimilarity.From the experimental results, the proposed method can produce meaningful, complete and internal-homogeneity divided region, moreover, the segmentation accuracy can meet the basic human visual requirements.

Key words: cloud model, wavelet denoising, harris operator, mutual information, graph theory, minimal spanning tree

中图分类号:

P237.4

宋岚, 文堂柳, 黎海生, 王杉. 基于云模型、图论和互信息的遥感影像分割方法[J]. 电子学报, 2015, 43(8): 1518-1525.

SONG Lan, WEN Tang-liu, LI Hai-sheng, WANG Shan. Segmentation Method for Remote Sensing Image Based on Cloud Model, Graph Theory and Mutual Information[J]. Acta Electronica Sinica, 2015, 43(8): 1518-1525.

参考文献

[1] A Mehnert,P Jackway.An improved seeded region growing algorithm[J].Pattern Recognition Letters,1997,18:1065-1071.
[2] 李德毅,杜益鸟 .不确定性人工智能[M].北京:国防工业出版社,2005.137-182. LiDeyi,Du Yi.Uncertainty Artificial Intelligence[M].Beijing:National Defence Industrial Press,2005.137-182.(in Chinese)
[3] 刘玉超,马于涛,张海粟,陈桂生.高阶高斯分布迭代的云模型及其数学性质研究[J].电子学报,2012,4(10):1913-1919. Liu Yuchao,Ma Yutao,Zhang Haisu,Chen Guisheng.Study on characters of cloud model based on high-order gaussian distribution with iterations[J].Acta Electronica Sinica,2012,4(10):1913-1919.(in Chinese)
[4] Felzenszwalb P F,Huttenlocher D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.
[5] Maes F,Collignon A.Multimodality image registration by maximization of mutual information[J].IEEE Trans Medical Image,1997,1(62):87-198.
[6] Harris C,Satephens M J.A combined corner and edge detector[J].Image Vision Computting,1998,6(1):121-128.
[7] 巩萍,潘冬明.小波分析及其在图像处理中的应用[J].长沙大学学报(自然科学版),2005,19(2):52-54. Gong Ping,Pan Dongming.Wavelet analysis and its application on image processing[J].Journal of Changsha University (Natural Science Edition),2005,19(2):52-54.(in Chinese)
[8] S G Mallat.Multiresolution approximations and wavelet orthogonal bases of Lz(R)[J].Trans Amer Math Soc,1989,315(1):69-87.
[9] S Mallat.A Wavelet Tour of Signal Processing[M].Boston Mass:Academic Press,1998.299-420.
[10] Harris C,Satephens M J.A combined corner and edge detector[J].Image Vision Computting,1998,6(1):121-128.
[11] 蒋嵘,李德毅,范建华.数值型数据的泛概念树的自动生成方法[J].计算机学报,2000,23(5):470-476. Jiang Rong,Li Deyi,Fan Jianhua.Automatic generation of pan-concept-tree on numerical data[J].Chinese Journal of Computers,2000,23(5):470-476.(in Chinese)
[12] 马建华,陈武凡,黄静,杨迪,毕一鸣.基于最大互信息量熵分割的CT金属伪影消除[J].电子学报,2009,37(8):1779-1783. Ma Jianhua,Chen Wufan,Huang Jing,Yang di,Bi Yiming.Metal artifact reduction in CT based on maximized the difference of mutual information segmentation[J].Acta Electronica Sinica,2009,37(8):1779-1783.(in Chinese)
[13] Baatz,M,Schäpe,A.Multiresolution segmentation-an optimization approach for high quality multi-scale image segmentation[A].Angewandte Geographische Informations-Verarbeitung XII[C].Karlsruhe:Wichmann Verlag,2000,12–23.
[14] Murtagh F.A survey of recent advances in hierarchical clustering algorit hms[ J].The Computer Journal,1983,26(4):354-359.
[15] J Shi,J Malik.Normalizedcuts and image segmentation[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[16] Pavan M,Pelillo M.A new graph heoretic approach to clustering and segmentation[J].Computer Vision and Pattern Recog- nition,2003,1(6):145-152.
[17] Kirkpatrick S,Gelatt C D,Vecchi M P.Optimization by simulated annealing[J].Science,1983,220(4598):671-680.

基于云模型、图论和互信息的遥感影像分割方法

Segmentation Method for Remote Sensing Image Based on Cloud Model, Graph Theory and Mutual Information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘润滋, 吴伟华, 张文柱, 周笛, 张琰. 基于图学习的密集空间网络传输资源调度方法[J]. 电子学报, 2021, 49(11): 2133-2137.
[2]	孙鑫威, 纪爱敏, 陈曦晖, 林新海, 许行. 强噪声背景下动车组轴承微弱故障信号检测[J]. 电子学报, 2021, 49(11): 2217-2224.
[3]	张泰江, 李勇军, 赵尚弘, 郑永兴, 辛宁. 基于代数连通度优化的空间信息网络分布式拓扑控制方法[J]. 电子学报, 2020, 48(6): 1162-1168.
[4]	杨晓玲, 冯山, 袁钟. 基于相对距离的反k近邻树离群点检测[J]. 电子学报, 2020, 48(5): 937-945.
[5]	尤殿龙, 郭松, 赵春慧, 原福永, 申利民, 陈真. 面向分类的流特征在线特征选择算法[J]. 电子学报, 2020, 48(2): 321-332.
[6]	彭丝雨, 周到, 张家琦, 王宇, 高军峰. 基于互信息的脑网络及测谎研究[J]. 电子学报, 2019, 47(7): 1551-1556.
[7]	李庆武, 马云鹏, 周亚琴, 邢俊. 基于无监督栈式降噪自编码网络的显著性检测算法[J]. 电子学报, 2019, 47(4): 871-879.
[8]	肖云鹏, 孙华超, 戴天骥, 李茜, 李暾. 一种基于云模型的社交网络推荐系统评分预测方法[J]. 电子学报, 2018, 46(7): 1762-1767.
[9]	雷维嘉, 宋海娜, 陈胜男, 谢显中. 基于无率纠错码和高阶QAM调制的收端速率自适应方案[J]. 电子学报, 2017, 45(8): 2001-2007.
[10]	马润年, 王班, 王刚, 郭晓成, 刘文斌. 基于互信息的通信网络节点重要性度量方法[J]. 电子学报, 2017, 45(3): 747-752.
[11]	张晴晖, 张榆锋, 林文晶, 周屹, 章克信, 高莲. 颈动脉B超估计血管壁搏动位移的干扰抑制[J]. 电子学报, 2017, 45(12): 2903-2908.
[12]	续欣莹, 张扩, 谢珺, 谢刚. 基于互信息下粒子群优化的属性约简算法[J]. 电子学报, 2017, 45(11): 2695-2704.
[13]	高洪波, 张新钰, 张天雷, 刘玉超, 李德毅. 基于云模型的智能驾驶车辆变粒度测评研究[J]. 电子学报, 2016, 44(2): 365-373.
[14]	肖云鹏, 姚豪豪, 刘宴兵. 一种基于云模型的WSNs节点信誉安全方案[J]. 电子学报, 2016, 44(1): 168-175.
[15]	陈波, 金添, 陆必应, 周智敏, 吴文浩. 穿墙雷达中基于最小生成树的建筑物内部结构重构技术[J]. 电子学报, 2015, 43(9): 1682-1688.