{"title":"基于可调模型的多光谱与全色图像融合方法。","authors":"Liangpei Zhang, Huanfeng Shen, Wei Gong, Hongyan Zhang","doi":"10.1109/TSMCB.2012.2198810","DOIUrl":null,"url":null,"abstract":"<p><p>In this paper, an adjustable model-based image fusion method for multispectral (MS) and panchromatic (PAN) images is developed. The relationships of the desired high spatial resolution (HR) MS images to the observed low-spatial-resolution MS images and HR PAN image are formulated with image observation models. The maximum a posteriori framework is employed to describe the inverse problem of image fusion. By choosing particular probability density functions, the fused HR MS images are solved using a gradient descent algorithm. In particular, two functions are defined to adaptively determine most regularization parameters using the partially fused results at each iteration, retaining one parameter to adjust the tradeoff between the enhancement of spatial information and the maintenance of spectral information. The proposed method has been tested using QuickBird and IKONOS images and compared to several known fusion methods using quantitative evaluation indices. The experimental results verify the efficacy of this method.</p>","PeriodicalId":55006,"journal":{"name":"IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TSMCB.2012.2198810","citationCount":"126","resultStr":"{\"title\":\"Adjustable model-based fusion method for multispectral and panchromatic images.\",\"authors\":\"Liangpei Zhang, Huanfeng Shen, Wei Gong, Hongyan Zhang\",\"doi\":\"10.1109/TSMCB.2012.2198810\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In this paper, an adjustable model-based image fusion method for multispectral (MS) and panchromatic (PAN) images is developed. The relationships of the desired high spatial resolution (HR) MS images to the observed low-spatial-resolution MS images and HR PAN image are formulated with image observation models. The maximum a posteriori framework is employed to describe the inverse problem of image fusion. By choosing particular probability density functions, the fused HR MS images are solved using a gradient descent algorithm. In particular, two functions are defined to adaptively determine most regularization parameters using the partially fused results at each iteration, retaining one parameter to adjust the tradeoff between the enhancement of spatial information and the maintenance of spectral information. The proposed method has been tested using QuickBird and IKONOS images and compared to several known fusion methods using quantitative evaluation indices. The experimental results verify the efficacy of this method.</p>\",\"PeriodicalId\":55006,\"journal\":{\"name\":\"IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1109/TSMCB.2012.2198810\",\"citationCount\":\"126\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TSMCB.2012.2198810\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2012/6/20 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TSMCB.2012.2198810","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2012/6/20 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
Adjustable model-based fusion method for multispectral and panchromatic images.
In this paper, an adjustable model-based image fusion method for multispectral (MS) and panchromatic (PAN) images is developed. The relationships of the desired high spatial resolution (HR) MS images to the observed low-spatial-resolution MS images and HR PAN image are formulated with image observation models. The maximum a posteriori framework is employed to describe the inverse problem of image fusion. By choosing particular probability density functions, the fused HR MS images are solved using a gradient descent algorithm. In particular, two functions are defined to adaptively determine most regularization parameters using the partially fused results at each iteration, retaining one parameter to adjust the tradeoff between the enhancement of spatial information and the maintenance of spectral information. The proposed method has been tested using QuickBird and IKONOS images and compared to several known fusion methods using quantitative evaluation indices. The experimental results verify the efficacy of this method.