{"title":"基于GMM的偏振分数分类统计模型","authors":"Ayush Chauhan, H. Maurya, R. K. Panigrahi","doi":"10.1109/APMC.2016.7931377","DOIUrl":null,"url":null,"abstract":"This paper presents a statistical model to classify the PolSAR image on the basis of Polarization Fraction (PF) of the backscattered wave. The basic principle behind PF, i.e., the relative power in the co-polarized and cross-polarized channel, is employed to distinguish between surface, double-bounce and volume scattering. We look to find the best fit model to the measured data by assuming it to be Gaussian distributed. A Radarsat-2 image of San Francisco is used to illustrate the results.","PeriodicalId":166478,"journal":{"name":"2016 Asia-Pacific Microwave Conference (APMC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Statistical modelling of Polarization Fraction for classification of PolSAR images using GMM\",\"authors\":\"Ayush Chauhan, H. Maurya, R. K. Panigrahi\",\"doi\":\"10.1109/APMC.2016.7931377\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a statistical model to classify the PolSAR image on the basis of Polarization Fraction (PF) of the backscattered wave. The basic principle behind PF, i.e., the relative power in the co-polarized and cross-polarized channel, is employed to distinguish between surface, double-bounce and volume scattering. We look to find the best fit model to the measured data by assuming it to be Gaussian distributed. A Radarsat-2 image of San Francisco is used to illustrate the results.\",\"PeriodicalId\":166478,\"journal\":{\"name\":\"2016 Asia-Pacific Microwave Conference (APMC)\",\"volume\":\"59 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 Asia-Pacific Microwave Conference (APMC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/APMC.2016.7931377\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Asia-Pacific Microwave Conference (APMC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APMC.2016.7931377","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Statistical modelling of Polarization Fraction for classification of PolSAR images using GMM
This paper presents a statistical model to classify the PolSAR image on the basis of Polarization Fraction (PF) of the backscattered wave. The basic principle behind PF, i.e., the relative power in the co-polarized and cross-polarized channel, is employed to distinguish between surface, double-bounce and volume scattering. We look to find the best fit model to the measured data by assuming it to be Gaussian distributed. A Radarsat-2 image of San Francisco is used to illustrate the results.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
