论文信息 - An assessment of some small window-based spatial features for land-cover classification

An assessment of some small window-based spatial features for land-cover classification

Fourteen small (3/spl times/3) window-based spatial measures are applied to a SPOT HRV multispectral Band 3 image to extract spatial features for the rural-urban fringe of Metropolitan Toronto, Canada. The spatial features are combined with the original image to identify 12 land-cover classes. Four classifiers were used in the study. Results show that when nine of the spatial features are in turn combined with the three original images, significantly improved classification accuracies (at the 95 percent confidence level) are obtained compared with using only the multispectral information from the three original images.<<ETX>>

P. Gong | P. Howarth | P. Gong | P.J. Howarth

[1] Jams L. Cushnie. The interactive effect of spatial resolution and degree of internal variability within land-cover types on classification accuracies , 1987 .

[2] Dong-Chen He,et al. Texture Unit, Texture Spectrum And Texture Analysis , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[3] Peng Gong,et al. A comparison of spatial feature extraction algorithms for land-use classification with SPOT HRV data , 1992 .

[4] Azriel Rosenfeld,et al. A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[5] P. Gong,et al. Frequency-based contextual classification and gray-level vector reduction for land-use identification , 1992 .

[6] J. R. Jensen. SPECTRAL AND TEXTURAL FEATURES TO CLASSIFY ELUSIVE LAND COVER AT THE URBAN FRINGE , 1979 .

[7] James R. Irons,et al. Texture transforms of remote sensing data , 1981 .

[8] P. Gong,et al. The use of structural information for improving land-cover classification accuracies at the rural-urban fringe. , 1990 .

[9] M.,et al. Statistical and Structural Approaches to Texture , 2022 .