基于主成分分析与粒子群优化的遥感影像变化检测
|
摘要
针对变化检测中差异影像上变化阈值选择困难的问题,该文提出了使用粒子群优化算法自动地从差异影像上选择最优变化阈值的方法。该方法首先利用主成分分析法从影像中提取包含最大信息的主分量,利用主分量构建差异影像;在此基础上,使用高斯混合模型估算差异影像的初始阈值,最后通过粒子群算法计算出最优的变化阈值。实验结果表明,该方法能够迅速地获取变化阈值,避免了人工选择时繁琐重复的尝试,且检测结果精度较高。
It is difficult to determine the changing threshold from difference image.In this paper,the particle swarm optimization(PSO)algorithm was used to choose optimal change threshold from the difference image.Firstly,the difference image was made by principal component analysis(PCA)method,which could extract the maximum information component from the remote sensing image.Then,PSO algorithm was used to obtain the optimal change threshold automatically and rapidly.Comparison result with the post-classification and CVA change detection methods indicated that the proposed method had higher accuracy and was more effective.
It is difficult to determine the changing threshold from difference image.In this paper,the particle swarm optimization(PSO)algorithm was used to choose optimal change threshold from the difference image.Firstly,the difference image was made by principal component analysis(PCA)method,which could extract the maximum information component from the remote sensing image.Then,PSO algorithm was used to obtain the optimal change threshold automatically and rapidly.Comparison result with the post-classification and CVA change detection methods indicated that the proposed method had higher accuracy and was more effective.
引文
[1]HUSSAIN M,CHEN D M,CHENG A,et al.Change detection from remotely sensed images:From pixelbased to object-based approaches[J].ISPRS Journal of Photogrammetry&Remote Sensing,2013,80(2):91-106.
[2]马建文,田国良,王长耀,等.遥感变化检测技术发展综述[J].地球科学进展,2004,19(2):192-196.(MA Jianwen,TIAN Guoliang,WANG Changyao,et al.Review of the development of remote sensing change detection technology[J].Advance in Earth Sciences,2004,19(2):192-196.)
[3]TIAN M H,WAN S H,YUE L H,et al.A novel approach for change detection in remote sensing image based on saliency map[C]//Computer Graphics,Imaging and Visualisation(CGIV 2007).Washington,DC,USA:IEEE Computer Society,2007:397-402.
[4]范海生,马蔼乃,李京.采用图像差值法提取土地利用变化信息方法:以攀枝花仁和区为例[J].遥感学报,2001,5(1):75-80.(FAN Haisheng,MA Ainai,LI Jing.Case study on image differencing method for land use change detection using thematic data in Renhe district of Panzhihua[J].Journal of Remote Sensing,2001,5(1):75-80.)
[5]吴柯,牛瑞卿,王毅,等.基于PCA与EM算法的多光谱遥感影像变化检测研究[J].计算机科学,2010,37(3):282-284.(WU Ke,NIU Ruiqing,WANG Yi,et al.Change detection of multi-spectral remote sensed images based on PCA and EM algorithm[J].Computer Science,2010,37(3):282-284.)
[6]赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.(ZHAO Yingshi.The principle and method of remote sensing application[M].Beijing:Science Press,2003.)
[7]龚浩,张景雄,申邵洪.基于对象的对应分析在高分辨率遥感影像变化检测中的应用[J].武汉大学学报(信息科学版),2009,34(5):544-547.(GONG Hao,ZHANG Jingxiong,SHEN Shaohong.Object-based correspondence analysis for improved accuracy in remote sensing change detection[J].Geomatics and Information Science of Wuhan University,2009,34(5):544-547.)
[8]WANG G X.An expert system for forest resource inventory and monitoring in the frame of multi-source data[M].Helsinki:University of Helsinki,1996.
[9]戴芹,刘建波,刘士彬.微粒群优化方法的遥感影像变化检测研究[J].测绘学报,2012,41(6):857-863.(DAI Qin,LIU Jianbo,LIU Shibin.Remote sensing image change detection using particle swarm optimization algorithm[J].Acta Geodaetica et Cartographica Sinica,2012,41(6):857-863.)
[10]龚纯.精通MATLAB最优化计算[M].北京:电子工业出版社,2009:270-275.(GONG Chun.Proficiency in MATLAB optimization algorithms[M].Beijing:Publishing House of Electronics Industry,2009:270-275.)
[2]马建文,田国良,王长耀,等.遥感变化检测技术发展综述[J].地球科学进展,2004,19(2):192-196.(MA Jianwen,TIAN Guoliang,WANG Changyao,et al.Review of the development of remote sensing change detection technology[J].Advance in Earth Sciences,2004,19(2):192-196.)
[3]TIAN M H,WAN S H,YUE L H,et al.A novel approach for change detection in remote sensing image based on saliency map[C]//Computer Graphics,Imaging and Visualisation(CGIV 2007).Washington,DC,USA:IEEE Computer Society,2007:397-402.
[4]范海生,马蔼乃,李京.采用图像差值法提取土地利用变化信息方法:以攀枝花仁和区为例[J].遥感学报,2001,5(1):75-80.(FAN Haisheng,MA Ainai,LI Jing.Case study on image differencing method for land use change detection using thematic data in Renhe district of Panzhihua[J].Journal of Remote Sensing,2001,5(1):75-80.)
[5]吴柯,牛瑞卿,王毅,等.基于PCA与EM算法的多光谱遥感影像变化检测研究[J].计算机科学,2010,37(3):282-284.(WU Ke,NIU Ruiqing,WANG Yi,et al.Change detection of multi-spectral remote sensed images based on PCA and EM algorithm[J].Computer Science,2010,37(3):282-284.)
[6]赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.(ZHAO Yingshi.The principle and method of remote sensing application[M].Beijing:Science Press,2003.)
[7]龚浩,张景雄,申邵洪.基于对象的对应分析在高分辨率遥感影像变化检测中的应用[J].武汉大学学报(信息科学版),2009,34(5):544-547.(GONG Hao,ZHANG Jingxiong,SHEN Shaohong.Object-based correspondence analysis for improved accuracy in remote sensing change detection[J].Geomatics and Information Science of Wuhan University,2009,34(5):544-547.)
[8]WANG G X.An expert system for forest resource inventory and monitoring in the frame of multi-source data[M].Helsinki:University of Helsinki,1996.
[9]戴芹,刘建波,刘士彬.微粒群优化方法的遥感影像变化检测研究[J].测绘学报,2012,41(6):857-863.(DAI Qin,LIU Jianbo,LIU Shibin.Remote sensing image change detection using particle swarm optimization algorithm[J].Acta Geodaetica et Cartographica Sinica,2012,41(6):857-863.)
[10]龚纯.精通MATLAB最优化计算[M].北京:电子工业出版社,2009:270-275.(GONG Chun.Proficiency in MATLAB optimization algorithms[M].Beijing:Publishing House of Electronics Industry,2009:270-275.)