摘要
The cloud cover for the South China Sea andits coastal area is relatively large throughout the year,which limits the potential application of optical remotesensing. A H J-charge-coupled device （HJ-CCD） has theadvantages of wide field, high temporal resolution, andshort repeat cycle. However, this instrument suffers fromits use of only four relatively low-quality bands whichcan＇t adequately resolve the features of long wavelengths.The Landsat Enhanced Thematic Mapper-plus （ETM＋）provides high-quality data, however, the Scan LineCorrector （SLC） stopped working and caused striping ofremote sensed images, which dramatically reduced thecoverage of the ETM＋ data. In order to combine theadvantages of the HJ-CCD and Landsat ETM＋ data, weadopted a back-propagation artificial neural network （BP-ANN） to fuse these two data types for this study. Theresults showed that the fused output data not only have theadvantage of data intactness for the HJ-CCD, but also havethe advantages of the multi-spectral and high radiometricresolution of the ETM＋ data. Moreover, the fused datawere analyzed qualitatively, quantitatively and from apractical application point of view. Experimental studiesindicated that the fused data have a full spatial distribution,multi-spectral bands, high radiometric resolution, a smalldifference between the observed and fused output data, anda high correlation between the observed and fused data.The excellent performance in its practical application is afurther demonstration that the fused data are of highquality.
The cloud cover for the South China Sea andits coastal area is relatively large throughout the year,which limits the potential application of optical remotesensing. A H J-charge-coupled device （HJ-CCD） has theadvantages of wide field, high temporal resolution, andshort repeat cycle. However, this instrument suffers fromits use of only four relatively low-quality bands whichcan＇t adequately resolve the features of long wavelengths.The Landsat Enhanced Thematic Mapper-plus （ETM＋）provides high-quality data, however, the Scan LineCorrector （SLC） stopped working and caused striping ofremote sensed images, which dramatically reduced thecoverage of the ETM＋ data. In order to combine theadvantages of the HJ-CCD and Landsat ETM＋ data, weadopted a back-propagation artificial neural network （BP-ANN） to fuse these two data types for this study. Theresults showed that the fused output data not only have theadvantage of data intactness for the HJ-CCD, but also havethe advantages of the multi-spectral and high radiometricresolution of the ETM＋ data. Moreover, the fused datawere analyzed qualitatively, quantitatively and from apractical application point of view. Experimental studiesindicated that the fused data have a full spatial distribution,multi-spectral bands, high radiometric resolution, a smalldifference between the observed and fused output data, anda high correlation between the observed and fused data.The excellent performance in its practical application is afurther demonstration that the fused data are of highquality.
