A morphology-based edge detection method has been used to study sea surface temperature (SST) fronts in the Taiwan Strait and its adjacent area. The method is based on mathematical morphology with multi-dimensional an...A morphology-based edge detection method has been used to study sea surface temperature (SST) fronts in the Taiwan Strait and its adjacent area. The method is based on mathematical morphology with multi-dimensional and multi-structural elements. Using six years’ SST data from September 2002 to August 2008, we distinguished the large SST front like Kuroshio Front as well as the smaller ones: namely Taiwan Bank Front, Zhe-Min Coastal Front and Zhang-Yun Ridge Front. The seasonal and monthly variations of these fronts were also studied. Generally, the SST fronts are stronger in winter but weaker in summer. And the fronts are at their active stage during the period from January to May but at their declining stage during the period from July to October.展开更多
Hyperspectral images in remote sensing include hundreds of spectral bands that provide valuable information for accurately identify objects.In this paper,a new method of classifying hyperspectral images using spectral...Hyperspectral images in remote sensing include hundreds of spectral bands that provide valuable information for accurately identify objects.In this paper,a new method of classifying hyperspectral images using spectral spatial information has been presented.Here,using the hyperspectral signal subspace identification(HYSIME)method which estimates the signal and noise correlation matrix and selects a subset of eigenvalues for the best representation of the signal subspace in order to minimize the mean square error,subsets from the main sample space have been extracted.After subspace extraction with the help of the HYSIME method,the edge-preserving filtering(EPF),and classification of the hyperspectral subspace using a support vector machine(SVM),results were then merged into the decision-making level using majority rule to create the spectral-spatial classifier.The simulation results showed that the spectral-spatial classifier presented leads to significant improvement in the accuracy and validity of the classification of Indiana,Pavia and Salinas hyperspectral images,such that it can classify these images with 98.79%,98.88% and 97.31% accuracy,respectively.展开更多
基金supported by National Basic Research Program of China (Grant Nos. 2007CB411803 and 2009CB421208)National Natural Science Foundation of China (Grant Nos. 40576015, 40821063 and 40810069004)
文摘A morphology-based edge detection method has been used to study sea surface temperature (SST) fronts in the Taiwan Strait and its adjacent area. The method is based on mathematical morphology with multi-dimensional and multi-structural elements. Using six years’ SST data from September 2002 to August 2008, we distinguished the large SST front like Kuroshio Front as well as the smaller ones: namely Taiwan Bank Front, Zhe-Min Coastal Front and Zhang-Yun Ridge Front. The seasonal and monthly variations of these fronts were also studied. Generally, the SST fronts are stronger in winter but weaker in summer. And the fronts are at their active stage during the period from January to May but at their declining stage during the period from July to October.
文摘Hyperspectral images in remote sensing include hundreds of spectral bands that provide valuable information for accurately identify objects.In this paper,a new method of classifying hyperspectral images using spectral spatial information has been presented.Here,using the hyperspectral signal subspace identification(HYSIME)method which estimates the signal and noise correlation matrix and selects a subset of eigenvalues for the best representation of the signal subspace in order to minimize the mean square error,subsets from the main sample space have been extracted.After subspace extraction with the help of the HYSIME method,the edge-preserving filtering(EPF),and classification of the hyperspectral subspace using a support vector machine(SVM),results were then merged into the decision-making level using majority rule to create the spectral-spatial classifier.The simulation results showed that the spectral-spatial classifier presented leads to significant improvement in the accuracy and validity of the classification of Indiana,Pavia and Salinas hyperspectral images,such that it can classify these images with 98.79%,98.88% and 97.31% accuracy,respectively.
