| Título: | Texture analysis for urban areas classification in high resolution satellite imagery |
| Autores: |
Massimiliano Basile Giannini; CNR Pasquale Merola Alessia Allegrini |
| Fecha: | 2012-08-17 |
| Publicador: | Applied Remote Sensing |
| Fuente: |
 |
| Tipo: |
Texture analysis, geostatistical analysis, object based classification |
| Tema: |
Remote Sensing texture analysis, co-occurrence measures, semivariogram |
| Descripción: | In this study the texture analysis is used to classify a high resolution QuickBird panchromatic image, in an urban area. The gray level cooccurrencematrix (GLCM) is computed to extract texture images. Texture measures are considered to be divided into three groups: Contrast,Orderliness and Statistic. The window size for the GLCM is determinated by semivariogram method. The principal component analysis(PCA) is then executed on texture images. The first few principal component bands (PCi), representing most of variations, are selected andassembled to panchromatic images. The selected PC bands, in conjunction with the original panchromatic image, are classified using anobject-based approach to categorize pixels into three classes: buildings, roads and vegetation. |
| Idioma: | Inglés |