Title :
Stochastic geometrical modeling for built-up area understanding from a single SAR intensity image with meter resolution
Author :
Quartulli, Marco ; Datcu, Mihai
Author_Institution :
Earth Obs. Dept., Adv. Comput. Syst., Rome, Italy
Abstract :
To investigate the limits and merits of information extraction from a single high-resolution synthetic aperture radar (SAR) backscatter image, we introduce a model-based algorithm for the automatic reconstruction of building areas from single-observation meter-resolution SAR intensity data. The reconstruction is based on the maximum a posteriori estimation by Monte Carlo methods of an optimal scene that is modeled as a set of mutually interacting Poisson-distributed marked points describing parametric building objects. Each of the objects can be hierarchically decomposed into a collection of radiometrically and geometrically specified object facets that in turn get mapped into data features by ground-to-range projection and inverse Gaussian statistics. The detection of the facets is based on a likelihood ratio. Results are presented for airborne data with resolutions in the range of 0.5-2 m on urban scenes covering agglomerations of buildings. To achieve robust results for building reconstruction, the integration with data from other sources is needed.
Keywords :
Gaussian processes; Monte Carlo methods; feature extraction; geophysical signal processing; image reconstruction; image resolution; maximum likelihood estimation; radar imaging; radar resolution; remote sensing by radar; synthetic aperture radar; terrain mapping; Monte Carlo methods; Poisson-distributed marked points; SAR backscatter image; airborne data; building reconstruction; built-up area understanding; data feature mapping; data integration; facet detection; geometrically specified object facets; ground-to-range projection; hierarchical Bayesian scene understanding; hierarchical decomposition; high resolution SAR; image reconstruction; information extraction; inverse Gaussian statistics; likelihood ratio; marked object process; marked point process; maximum a posteriori estimation; optimal scene modeling; parametric building objects; radiometrically specified object facets; single-observation meter-resolution SAR intensity data; stochastic geometrical modeling; synthetic aperture radar; urban scene covering agglomerations; Backscatter; Data mining; Face detection; Image reconstruction; Image resolution; Layout; Maximum a posteriori estimation; Solid modeling; Stochastic processes; Synthetic aperture radar; Hierarchical Bayesian scene understanding; SAR; high-resolution synthetic aperture radar; marked point/object processes; urban scenes;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
DOI :
10.1109/TGRS.2004.833391
