Title :
Improved VHR Urban Area Mapping Exploiting Object Boundaries
Author :
Gamba, Paolo ; Dell´Acqua, Fabio ; Lisini, Gianni ; Trianni, Giovanna
Author_Institution :
IEEE, Shanghai
Abstract :
In this paper, a mapping procedure exploiting object boundaries in very high-resolution (VHR) images is proposed. After discrimination between boundary and nonboundary pixel sets, each of the two sets is separately classified. The former are labeled using a neural network (NN), and the shape of the pixel set is finely tuned by enforcing a few geometrical constraints, while the latter are classified using an adaptive Markov random field (MRF) model. The two mapping outputs are finally combined through a decision fusion process. Experimental results on hyperspectral and satellite VHR imagery show the superior performance of this method over conventional NN and MRF classifiers.
Keywords :
Markov processes; neural nets; terrain mapping; adaptive Markov random field model; decision fusion process; neural networks; object boundaries; urban area mapping; very high-resolution images; Geographic Information Systems; Hyperspectral sensors; Image segmentation; Markov random fields; Neural networks; Remote sensing; Shape; Solid modeling; Spatial resolution; Urban areas; Land cover mapping; spatially adaptive classifier; urban remote sensing; very high-resolution (VHR) sensors;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
DOI :
10.1109/TGRS.2007.899811
