In this study,analyses are conducted on the information features of a construction site,a cornfield and subsidence seeper land in a coal mining area with a synthetic aperture radar (SAR) image of medium resolution. Ba...In this study,analyses are conducted on the information features of a construction site,a cornfield and subsidence seeper land in a coal mining area with a synthetic aperture radar (SAR) image of medium resolution. Based on features of land cover of the coal mining area,on texture feature extraction and a selection method of a gray-level co-occurrence matrix (GLCM) of the SAR image,we propose in this study that the optimum window size for computing the GLCM is an appropriate sized window that can effectively distinguish different types of land cover. Next,a band combination was carried out over the text feature images and the band-filtered SAR image to secure a new multi-band image. After the transformation of the new image with principal component analysis,a classification is conducted selectively on three principal component bands with the most information. Finally,through training and experimenting with the samples,a better three-layered BP neural network was established to classify the SAR image. The results show that,assisted by texture information,the neural network classification improved the accuracy of SAR image classification by 14.6%,compared with a classification by maximum likelihood estimation without texture information.展开更多
Based on satellite remote sensing TM/ETM+ images of Xuzhou city,land use forms of the city in 1987,1994 and 2000 were extracted by using a neural network classification method. The expansion contribution rate and annu...Based on satellite remote sensing TM/ETM+ images of Xuzhou city,land use forms of the city in 1987,1994 and 2000 were extracted by using a neural network classification method. The expansion contribution rate and annual expansion intensity index of each administrative district have been calculated and the contribution rate matrices and spatial distribution maps of land use changes were obtained. Based on the above analysis,the characteristics of urban expansion from 1987 to 2000 have been explored. From 1987 to 1994,the expansion contribution rate of Quanshan dis-trict reached 46.80%,the highest in all administrative districts of Xuzhou city; Tongshan town was in a high-speed ex-pansion period; both Quanshan and Yunlong districts were experiencing fast-speed expansion periods while the entire city was expanding at a medium-speed with an annual expansion intensity index of 0.98; the city spread eastwards and southwards. From 1994 to 2000,the expansion contribution rate of Quanshan district reached 43.67%,the highest in Xuzhou; the entire city was in a medium-speed expansion period with an annual expansion intensity index of 1.04; the city has rapidly been extended towards the southeast. According to the contribution rate matrices of land use changes,urban expansion mainly usurps cropland and woodland. A quantitative analysis found that population growth,indus-trialization and economic development are the primary driving forces behind urban expansion.展开更多
In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree alg...In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree algorithm,spectral absorption index (SAI),continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets,and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA),minimum noise fraction (MNF),grouping PCA,and derivate spectral analysis,the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM,and SVM outperforms traditional SAM and MLC classifiers for OMIS data.展开更多
Based on the satellite remote sensing TM/ETM images of Xuzhou city, basic data about land use of the city from 1994 to 2000 are obtained with the neural network classification module of PCI software, and the dynamic c...Based on the satellite remote sensing TM/ETM images of Xuzhou city, basic data about land use of the city from 1994 to 2000 are obtained with the neural network classification module of PCI software, and the dynamic con- version matrix of land use is thus calculated. The areas of construction land and water body have increased by 1833.93 hm2 and 804.87 hm2, respectively. On the contrary, the area of cropland has decreased by 3207.24 hm2. The area of cropland converted into construction land makes up 26.84%, and that converted into water body amounts for 8.17% of the total area of cropland in 1994. The variation index of land use degree and the dynamic degree index of land use computed are 1.38 and 57.81%, respectively, which demonstrate that land use in Xuzhou is in a development period and the changes are drastic. The frequency index and importance index of the form in which cropland converted into con- struction land are 29.91% and 68.93% respectively. The results indicate that the change is not only widespread in space but a major form of spatial change of land use in the area.展开更多
基金Projects 40771143 supported by the National Natural Science Foundation of China2007AA12Z162 by the Hi-tech Research and Development Program of China
文摘In this study,analyses are conducted on the information features of a construction site,a cornfield and subsidence seeper land in a coal mining area with a synthetic aperture radar (SAR) image of medium resolution. Based on features of land cover of the coal mining area,on texture feature extraction and a selection method of a gray-level co-occurrence matrix (GLCM) of the SAR image,we propose in this study that the optimum window size for computing the GLCM is an appropriate sized window that can effectively distinguish different types of land cover. Next,a band combination was carried out over the text feature images and the band-filtered SAR image to secure a new multi-band image. After the transformation of the new image with principal component analysis,a classification is conducted selectively on three principal component bands with the most information. Finally,through training and experimenting with the samples,a better three-layered BP neural network was established to classify the SAR image. The results show that,assisted by texture information,the neural network classification improved the accuracy of SAR image classification by 14.6%,compared with a classification by maximum likelihood estimation without texture information.
基金Projects 40401038 supported by the National Natural Science Foundation of China05KJB420133 by the Natural Science Foundation for Colleges and Universities in Jiangsu Province
文摘Based on satellite remote sensing TM/ETM+ images of Xuzhou city,land use forms of the city in 1987,1994 and 2000 were extracted by using a neural network classification method. The expansion contribution rate and annual expansion intensity index of each administrative district have been calculated and the contribution rate matrices and spatial distribution maps of land use changes were obtained. Based on the above analysis,the characteristics of urban expansion from 1987 to 2000 have been explored. From 1987 to 1994,the expansion contribution rate of Quanshan dis-trict reached 46.80%,the highest in all administrative districts of Xuzhou city; Tongshan town was in a high-speed ex-pansion period; both Quanshan and Yunlong districts were experiencing fast-speed expansion periods while the entire city was expanding at a medium-speed with an annual expansion intensity index of 0.98; the city spread eastwards and southwards. From 1994 to 2000,the expansion contribution rate of Quanshan district reached 43.67%,the highest in Xuzhou; the entire city was in a medium-speed expansion period with an annual expansion intensity index of 1.04; the city has rapidly been extended towards the southeast. According to the contribution rate matrices of land use changes,urban expansion mainly usurps cropland and woodland. A quantitative analysis found that population growth,indus-trialization and economic development are the primary driving forces behind urban expansion.
基金Projects 40401038 and 40871195 supported by the National Natural Science Foundation of ChinaNCET-06-0476 by the Program for New Century Excellent Talents in University20070290516 by the Specialized Research Fund for the Doctoral Program of Higher Education
文摘In order to combine feature extraction operations with specific hyperspectral remote sensing information processing objectives,two aspects of feature extraction were explored. Based on clustering and decision tree algorithm,spectral absorption index (SAI),continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of different targets,and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA),minimum noise fraction (MNF),grouping PCA,and derivate spectral analysis,the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM,and SVM outperforms traditional SAM and MLC classifiers for OMIS data.
基金Projects 40401038 supported by National Natural Science Foundation of China, and 05KJB420133 by Natural Science Foundation for Colleges and Universities in Jiangsu Province
文摘Based on the satellite remote sensing TM/ETM images of Xuzhou city, basic data about land use of the city from 1994 to 2000 are obtained with the neural network classification module of PCI software, and the dynamic con- version matrix of land use is thus calculated. The areas of construction land and water body have increased by 1833.93 hm2 and 804.87 hm2, respectively. On the contrary, the area of cropland has decreased by 3207.24 hm2. The area of cropland converted into construction land makes up 26.84%, and that converted into water body amounts for 8.17% of the total area of cropland in 1994. The variation index of land use degree and the dynamic degree index of land use computed are 1.38 and 57.81%, respectively, which demonstrate that land use in Xuzhou is in a development period and the changes are drastic. The frequency index and importance index of the form in which cropland converted into con- struction land are 29.91% and 68.93% respectively. The results indicate that the change is not only widespread in space but a major form of spatial change of land use in the area.
