This paper proposes a multiscale method based on the concept of lacunarity to recognize and classify textures of remote sensing images from urban areas with different inhabitability conditions. Experiments were done with several fragments of Recife (northeast of Brazil) intra-urban tissue. The results suggest that it is possible to describe and distinguish spatial patterns through its textures, and that there is a strong correlation between its morphological and social patterns.
Lacunarity curves from 30 QuickBird satellite images of Recife, Brazil from urban areas with high (green curves on the graph) and low (red curves on the graph) inhabitability. For more information, see the paper: urban texture: a multiscale analysis of sociospatial patterns which was presented at 10th International Conference on Computers in Urban Planning and Urban Management CUPUM 2007 .
