{"title":"基于中分辨率Lansat TM影像的绿洲沙漠植被信息提取方法——以也门瓦迪哈德拉穆特沙漠为例","authors":"A. Almhab, I. Busu","doi":"10.1109/AMS.2008.143","DOIUrl":null,"url":null,"abstract":"This paper present two issues namely; firest is oasis desert brightness inversion correction, and secondly, the classifying method of oasis desert vegetation through remote sensing image data. Oasis desert brightness inversion is known reduce the classification accuracy in medium-resolution images. In this study, the radiation correction and the brightness inversion adjustment models was analysis. The model's parameters were obtained from the image pixel values. The result of brightness inversion correction shows that the model can correct oasis desert brightness inversion. After brightness inversion correction, the vegetation's pixel value in brightness inversion area is similar with the pixel value of vegetation in other area. Brightness inversion correction increases classification accuracy. In the second part of this study, three methods are studied to derive oasis desert vegetations information, including vegetation index method, back propagation neural network method, and texture method. Three methods' classification accuracies are calculated and appraised. And a conclusion is drawn, which is the texture classification method is a good classification method. The accuracy of texture classification method can reach up to 82.31%.","PeriodicalId":122964,"journal":{"name":"2008 Second Asia International Conference on Modelling & Simulation (AMS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"The Approaches for Oasis Desert Vegetation Information Abstraction Based on Medium-Resolution Lansat TM Image: A Case Study in Desert wadi Hadramut Yemen\",\"authors\":\"A. Almhab, I. Busu\",\"doi\":\"10.1109/AMS.2008.143\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper present two issues namely; firest is oasis desert brightness inversion correction, and secondly, the classifying method of oasis desert vegetation through remote sensing image data. Oasis desert brightness inversion is known reduce the classification accuracy in medium-resolution images. In this study, the radiation correction and the brightness inversion adjustment models was analysis. The model's parameters were obtained from the image pixel values. The result of brightness inversion correction shows that the model can correct oasis desert brightness inversion. After brightness inversion correction, the vegetation's pixel value in brightness inversion area is similar with the pixel value of vegetation in other area. Brightness inversion correction increases classification accuracy. In the second part of this study, three methods are studied to derive oasis desert vegetations information, including vegetation index method, back propagation neural network method, and texture method. Three methods' classification accuracies are calculated and appraised. And a conclusion is drawn, which is the texture classification method is a good classification method. The accuracy of texture classification method can reach up to 82.31%.\",\"PeriodicalId\":122964,\"journal\":{\"name\":\"2008 Second Asia International Conference on Modelling & Simulation (AMS)\",\"volume\":\"44 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-05-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 Second Asia International Conference on Modelling & Simulation (AMS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AMS.2008.143\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 Second Asia International Conference on Modelling & Simulation (AMS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AMS.2008.143","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The Approaches for Oasis Desert Vegetation Information Abstraction Based on Medium-Resolution Lansat TM Image: A Case Study in Desert wadi Hadramut Yemen
This paper present two issues namely; firest is oasis desert brightness inversion correction, and secondly, the classifying method of oasis desert vegetation through remote sensing image data. Oasis desert brightness inversion is known reduce the classification accuracy in medium-resolution images. In this study, the radiation correction and the brightness inversion adjustment models was analysis. The model's parameters were obtained from the image pixel values. The result of brightness inversion correction shows that the model can correct oasis desert brightness inversion. After brightness inversion correction, the vegetation's pixel value in brightness inversion area is similar with the pixel value of vegetation in other area. Brightness inversion correction increases classification accuracy. In the second part of this study, three methods are studied to derive oasis desert vegetations information, including vegetation index method, back propagation neural network method, and texture method. Three methods' classification accuracies are calculated and appraised. And a conclusion is drawn, which is the texture classification method is a good classification method. The accuracy of texture classification method can reach up to 82.31%.