论文信息 - Monitoring settlement dynamics by anisotropic textural analysis of panchromatic VHR data

Monitoring settlement dynamics by anisotropic textural analysis of panchromatic VHR data

A procedure for the calculation of a "built-up presence index" is presented. The index is based on fuzzy rule-based composition of anisotropic textural measures derived from the satellite data by the gray-level co-occurrence matrix (GLCM). The case study includes multi-temporal analysis, wide area coverage (65times135 kilometers) with multiple datasets, scattered settlements, and presence of arid and semi-arid areas together with complex agricultural landscape in the background. The concept is validated comparing the output of the procedure with and exhaustive reference dataset covering 218.23 square kilometers.

M. Pesaresi | A. Gerhardinger | F. Kayitakire

[1] Robert M. Haralick,et al. Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2] R.M. Haralick,et al. Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

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

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

[5] Peng Gong,et al. Study of urban spatial patterns from SPOT panchromatic imagery using textural analysis , 2003 .

[6] Dongmei Chen,et al. Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case , 2004 .

[7] Anne Puissant,et al. The utility of texture analysis to improve per‐pixel classification for high to very high spatial resolution imagery , 2005 .