半监督离散势理论在遥感影像变化检测中的应用

doi:10.13474/j.cnki.11-2246.2019.0251

测绘通报 ›› 2019, Vol. 0 ›› Issue (8): 54-58.doi: 10.13474/j.cnki.11-2246.2019.0251

半监督离散势理论在遥感影像变化检测中的应用

谢福鼎¹, 赫佳妮¹, 郑宏亮²

1. 辽宁师范大学城市与环境学院, 辽宁大连 116029;
2. 辽宁师范大学计算机与信息技术学院, 辽宁大连 116081

收稿日期:2018-10-22 出版日期:2019-08-25 发布日期:2019-09-06
通讯作者: 郑宏亮。E-mail:zheng-hl@263.net E-mail:zheng-hl@263.net
作者简介:谢福鼎(1965-),男,博士,教授,研究方向为模式识别、遥感影像处理。E-mail:1075939185@qq.com
基金资助:
国家自然科学基金（41771178；61772252）

Application of semi-supervised discrete potential theory in remote sensing image change detection

XIE Fuding¹, HE Jiani¹, ZHENG Hongliang²

1. College of Urban and Environment, Liaoning Normal University, Dalian 116029, China;
2. College of Computer science, Liaoning Normal University, Dalian 116081, China

Received:2018-10-22 Online:2019-08-25 Published:2019-09-06

摘要/Abstract

摘要： 随着遥感技术的发展，遥感影像变化检测作为一种有效的技术手段，在环境监测、灾害救援等领域发挥了重要作用。然而地物复杂、标记困难等问题导致有效的变化检测存在一定的困难。本文提出了一种基于半监督离散势理论的遥感影像变化检测方法。该方法首先采用一种新的标记样本点的方法得到训练集，然后利用KNN方法构造复杂网络，最后对复杂网络中经典Wu-Huberman算法进行改进并划分网络。所得到的两个社团结构恰好对应了变化部分和不变部分。试验结果表明，基于半监督离散势理论的变化检测方法具有良好的变化检测性能。

关键词: 遥感图像, 变化检测, 半监督分类, 离散势理论, Wu-Huberman算法

Abstract: With the development of remote sensing technology, change detection for remote sensing image provides an effective method in environmental monitoring, disaster relief and many other fields. However, it is still a challenging problem to develop more effective change detection methods due to the complexity of ground-truth and the difficulty of labeling the samples and so on. This paper proposes a remote sensing image change detection method based on semi-supervised discrete potential theory. The suggested method first uses a new method to label the samples to get the training set, then constructs complex network by KNN approach. Finally, it improves the classical Wu-Huberman algorithm in complex network and divides the network. As a result, the obtained two community structures exactly correspond to the change part and the invariant part. Experimental results show that the change detection method based on semi-supervised discrete potential theory has perfect change detection performance.

Key words: remote sensing image, change detection, semi-supervised classification, discrete potential theory, Wu-Huberman algorithm

中图分类号:

P237

谢福鼎, 赫佳妮, 郑宏亮. 半监督离散势理论在遥感影像变化检测中的应用[J]. 测绘通报, 2019, 0(8): 54-58.

XIE Fuding, HE Jiani, ZHENG Hongliang. Application of semi-supervised discrete potential theory in remote sensing image change detection[J]. 测绘通报, 2019, 0(8): 54-58.

参考文献

[1] LIU Q, LIU L, WANG Y. Unsupervised change detection for multispectral remote sensing images using random walks[J]. Remote Sensing, 2017, 9(5):438.
[2] AWRANGJEB M. Effective generation and update of a building map database through automatic building change detection from LiDAR point cloud data[J]. Remote Sensing, 2015, 7(10):14119-14150.
[3] VITTEK M, BRINK A, DONNAY F, et al. Land cover change monitoring using landsat MSS/TM satellite image data over West Africa between 1975 and 1990[J]. Remote Sensing, 2014, 6(1):658-676.
[4] LEI T, XUE D, LV Z, et al. Unsupervised change detection using fast fuzzy clustering for landslide mapping from very high-resolution images[J]. Remote Sensing, 2018, 10(9):1381.
[5] BYUN Y, HAN Y, CHAE T. Image fusion-based change detection for flood extent extraction using bi-temporal very high-resolution satellite images[J]. Remote Sensing, 2015, 7(8):10347-10363.
[6] LUO H, LIU C, WU C, et al. Urban change detection based on Dempster-Shafer theory for multitemporal very high-resolution imagery[J]. Remote Sensing, 2018, 10(7):980.
[7] 施文灶,毛政元.基于图分割的高分辨率遥感影像建筑物变化检测研究[J].地球信息科学学报,2016,18(3):423-432.
[8] 张志强,张新长,辛秦川,等.结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J].测绘学报,2018,47(1):102-112.
[9] 郝明. 基于空间信息准确性增强的遥感影像变化检测方法研究[D]. 徐州:中国矿业大学, 2015.
[10] HOU B, WANG Y, LIU Q. A saliency guided semi-supervised building change detection method for high resolution remote sensing images[J]. Sensors, 2016, 16(9):1377.
[11] 赵磊,王斌,张立明.基于分割窗半监督支持向量机的遥感图像变化检测[J].复旦学报(自然科学版),2010,49(2):190-196.
[12] 高桂荣,严威,夏晨阳,等.结合空间信息的PTSVM的遥感图像变化检测[J].电子测量技术,2016,39(4):45-48,52.
[13] LAL A M, ANOUNCIA S M. Semi-supervised change detection approach combining sparse fusion and constrained k means for multi-temporal remote sensing images[J]. The Egyptian Journal of Remote Sensing and Space Science, 2015, 18(2):279-288.
[14] 谢福鼎,于珊珊,杨俊.一种新的融合空间信息的半监督变化监测方法[J].测绘通报,2018(1):50-54.
[15] 汪小帆,李翔,陈关荣. 复杂网络理论及其应用[M].北京:清华大学出版社,2006.
[16] JI M,ZHANG D,XIE F,et al.Semi-supervised community detection by voltage drops[J]. Mathematical Problems in Engineering,2016(1):1-10.

半监督离散势理论在遥感影像变化检测中的应用

Application of semi-supervised discrete potential theory in remote sensing image change detection

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

本文评价

[1]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.
[2]	潘建平, 李鑫, 孙博文, 胡勇, 李明明. 基于注意力密集连接金字塔网络的新增建设用地变化检测[J]. 测绘通报, 2022, 0(3): 41-46,59.
[3]	杨景玉, 贾多科, 王阳萍. 基于超像素分割与CRF的高分辨率遥感影像变化检测[J]. 测绘通报, 2022, 0(2): 25-30,49.
[4]	乐颖, 夏元平. 基于比值法的多源多时相数据城区变化检测[J]. 测绘通报, 2022, 0(2): 56-61.
[5]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[6]	周秀华, 李乃强. 基于多种相似度特征的道路实体融合方法[J]. 测绘通报, 2021, 0(8): 102-105,157.
[7]	苏艺凡, 党建武, 王阳萍, 杨景玉. 改进的区间二型模糊聚类遥感影像变化检测[J]. 测绘通报, 2021, 0(7): 44-51,58.
[8]	刘海飞, 杨敏华, 王晶, 徐刚, 陈杰. 利用结构面对象的高分遥感影像建筑物变化检测[J]. 测绘通报, 2021, 0(6): 16-20.
[9]	张玉, 贾遂民. 噪声调节主成分变换下的遥感图像薄云去除[J]. 测绘通报, 2021, 0(3): 33-37.
[10]	张伟良, 刘琦, 吴长彬, 杨光迪. 基于孪生神经网络的土地利用现状年度变化检测[J]. 测绘通报, 2021, 0(3): 91-95,104.
[11]	赖正文, 夏小云. 像素级和对象级高分辨率遥感图像变化检测分析[J]. 测绘通报, 2021, 0(2): 59-63.
[12]	孙玉梅, 刘昱豪, 边占新, 孙亮, 陈敬周. 深度学习PaddlePaddle框架支持下的遥感智能视觉平台研究与实现[J]. 测绘通报, 2021, 0(11): 65-69,75.
[13]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[14]	韩建平. 青海省地震灾后地物变化的快速识别[J]. 测绘通报, 2021, 0(11): 120-123.
[15]	韩建平. 基于遥感影像的青海省环境变化监测[J]. 测绘通报, 2021, 0(10): 123-126,145.