结合变化向量分析和直觉模糊聚类的遥感影像变化检测方法

季欣然; 黄亮; 陈朋弟

doi:10.13442/j.gnss.1008-9268.2020.06.015

结合变化向量分析和直觉模糊聚类的遥感影像变化检测方法

季欣然¹,
黄亮^1,2, ,,
陈朋弟¹

1. 昆明理工大学国土资源工程学院, 昆明 650093;
2. 云南省高校高原山区空间信息测绘技术应用工程研究中心, 昆明 650093

基金项目:

国家自然科学基金（41961039，41961053）；云南省应用基础研究计划面上项目（2018FB078）；云南省高校工程中心建设计划资助的课题

详细信息

作者简介:
季欣然(1998-),女,硕士研究生,研究方向为遥感影像变化检测.

黄亮(1985-),男,博士,副教授,硕士研究生导师,研究方向为遥感图像处理与分析.

陈朋弟(1993-),男,硕士研究生,研究方向为遥感影像目标检测.

通信作者:
黄亮 E-mail:kmhuangliang@163.com

中图分类号: P237
计量
- 文章访问数: 414
- HTML全文浏览量: 82
- PDF下载量: 16
出版历程
- 收稿日期: 2020-09-15
- 网络出版日期: 2021-04-08
- 刊出日期: 2020-12-29

Change detection in remote sensing images combined with intuitionistic fuzzy clustering and change vector analysis

1. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China;
2. Surveying and Mapping Geo-Informatics Technology Research Center on Plateau Mountains of Yunnan Higher Education, Kunming 650093, China

摘要

摘要: 针对多时相遥感影像变化检测存在数据不确定性、检测精度不高等问题，提出了一种结合变化向量分析（CVA）和直觉模糊C均值聚类算法（IFCM）的多时相遥感影像变化检测方法. 首先通过CVA构建两个时相遥感影像的差异影像；然后采用直觉模糊C均值聚类算法对差异影像进行聚类得出变化区域和未变化区域；最后对变化检测结果进行二值化处理并进行精度评价. 选取两个时相的高分一号遥感影像和Szada数据集影像作为实验数据. 实验结果表明，采用提出的方法可有效解决传统方法存在的数据不确定性问题，变化检测精度达到了95.92%和92.70%，是一种可行的遥感影像变化检测方法. 研究结果可用于森林动态变化监测、土地复垦利用规划变化分析以及灾损评估.
- 直觉模糊C均值聚类 /
- 变化向量分析 /
- 变化检测 /
- 高分一号卫星 /
- 遥感影像
Abstract: Aiming at the problems of multi-temporal remote sensing images change detection with data uncertainty and low detection accuracy, a multi-temporal remote sensing images change detection method combined with change vector analysis (CVA) and intuitionistic fuzzy C-means clustering algorithm (IFCM) is proposed. Firstly, the difference image of bi-temporal remote sensing images is obtained by change vector analysis method. Then the difference image is clustered by the intuitionistic fuzzy C-means clustering algorithm to obtain the change areas and the non-change areas. Finally, the change detection results are binarized and the accuracy is evaluated. The bi-temporal Gaofeng-1 remote sensing images and Szada image data sets were selected as experimental data. The experimental results show that the proposed method can effectively solve the data uncertainty problem existing in the traditional method, it is a feasible remote sensing images change detection method. The overall accuracy of change detection achieved 95.92% and 92.70%. The research results can be used for forest dynamic change monitoring, land reclamation utilization planning change analysis and damage assessment.
- intuitionistic fuzzy c-means clustering /
- change vector analysis /
- change detection /
- gaofeng-1 satellite /
- remote sensing image

HTML全文

参考文献(25)

张良培,武辰.多时相遥感影像变化检测的现状与展望[J].测绘学报,2017,46(10):1447-1459.

黄亮,姚丙秀,陈朋弟,等.高分辨率遥感影像超像素的模糊聚类分割法[J].测绘学报,2020,49(5):589-597.

李德仁.利用遥感影像进行变化检测[J].武汉大学学报(信息科学版), 2003,28(增刊):7-12.

HUANG L,PENG Q Z,YU X Q.Change detection in multitemporal high spatial resolution remote-sensing images based on saliency detection and spatial intuitionistic fuzzy C-means clustering[J].Journal of spectroscopy,2020(7):1-9.DOI: 10.1155/2020/2725186.

黄亮.多时相遥感影像变化检测技术研究[J].测绘学报,2020,49(6):801.

史文中,张鹏林.光学遥感影像变化检测研究的回顾与展望[J].武汉大学学报(信息科学版),2018,43(12):1832-1837.

眭海刚,冯文卿,李文卓,等.多时相遥感影像变化检测方法综述[J].武汉大学学报(信息科学版),2018,43(12):1885-1898.

赵磊,王斌,张立明.基于模糊C均值聚类和邻域分析的无监督多通道遥感图像变化检测[J].数据采集与处理,2011,26(4):395-401.

WU C,WU Y Q.Multitemporal images change detection using nonsubsampled contourlet transform and kernel fuzzy C-means clustering[C]//20112nd International Symposium on Intelligence Information Processing and Trusted Computing,2011.DOI: 10.1109/IPTC.2011.31.

MA W P,JIAO L C,GONG M G,et al.Image change detection based on an improved rough fuzzy C-means clustering algorithm[J].International journal of machine learning and cybernetics,2014,5(3):369-377.DOI: 10.1007/s13042-013-0174-4.

YAN W D,SHI S J,PAN L L,et al.Unsupervised change detection in SAR images based on frequency difference and a modified fuzzy C-means clustering[J].International journal of remote sensing,2018,39(10):3055-3075.DOI: 10.1080/01431161.2018.1434325.

王建明,史文中,邵攀.自适应距离和模糊拓扑优化的模糊聚类SAR影像变化检测[J].测绘学报,2018,47(5):611-619.

王峰萍,王卫星,高婷,等.基于离散小波变换和邻域模糊C均值的变化检测方法[J].西北工业大学学报,2018,36(3):426-431.

刘陆洋,贾振红,杨杰,等.利用双差异图和PCA的SAR图像变化检测[J].计算机工程与设计,2019,40(7):2002-2006.

张岭军,李聪,段云龙.结合空间邻域信息的SAR图像变化检测[J].计算机工程与应用,2019,55(15):185-192.

ZADEH L A.Fuzzy sets as a basis for a theory of possibility[J].Fuzzy sets and systems,1978,1(1):3-28.DOI: 10.1016/0165-0114(78)90029-5.

YAGER R R.On the measure of fuzziness and negation.II.Lattices[J].Information and control,1980,44(3):236-260.DOI: 10.1016/s0019-9958(80)90156-4.

赵辽英,陈小芬,厉小润.变化向量分析结合光谱解混的高光谱变化检测[J].浙江大学学报(工学版),2017,51(10):1912-1919.

常方正,赵银娣,刘善磊.遥感影像CVA变化检测的CUDA并行算法设计[J].遥感学报,2016,20(1):114-128.

JOHNSON R D,KASISCHKE E S.Change vector analysis:a technique for the multispectral monitoring of land cover and condition[J].International journal of remote sensing,1998,19(3):411-426.DOI: 10.1080/014311698216062.

贾彩杰.基于模糊聚类算法的遥感图像变化检测的研究[D].西安:西安电子科技大学,2013.

TRIPATHY B K,BASAN A,GOVEL S.Image segmentation using spatial intuitionistic fuzzy C means clustering[C]//2014 IEEE International Conference on Computational Intelligence and Computing Research,2014.DOI: 10.1109/ICCIC.2014.7238446.

王铭佳,黄亮.利用指数熵的多时相遥感影像变化检测方法[J].遥感信息, 2017,32(3):81-85.

KRINIDIS S,CHATZIS V.A robust fuzzy local information C-means clustering algorithm[J].IEEE transactions on image processing,2010,19(5):1328-1337.DOI: 10.1109/TIP.2010.2040763.

HUANG L,FANG Y M,ZUO X Q,et al.Automatic change detection method of multitemporal remote sensing images based on 2D-otsu algorithm improved by firefly algorithm[J].Journal of sensors,2015:1-8.DOI: 10.1155/2015/327123.

施引文献(4)

期刊类型引用(2)

1.	高建文，管海燕，彭代锋，许正森，康健，季雅婷，翟若雪. 基于局部-全局语义特征增强的遥感影像变化检测网络模型. 地球信息科学学报. 2023(03): 625-637 . 百度学术
2.	邵攀，范红梅，高梓昂. 基于自适应半监督模糊C均值的遥感变化检测. 地球信息科学学报. 2022(03): 508-521 . 百度学术