Incorporating spectral, texture, and shape information for high spatial resolution satellite imagery classification

Abstract

Texture and shape analysis offer interesting possibilities to characterize the structural heterogeneity of classes in the high spatial resolution satellite imagery. In this paper, texture features are generated based on the Gaussian Markov random field (GMRF) model, and shape features are measured using geometric moments. Then feature selection is implemented according to the class separability. To reduce the border blurring effect introduced by texture features, the unsupervised classification algorithm involved ordered procedures is proposed, in which linear objects are extracted using spectral and shape features firstly, then other objects are detected using the combination of spectral, texture, and shape features. The proposed classification method is implemented using QuickBird imagery. For comparison, the standard K-means method with spectral data is used as a benchmark. The experimental results show that the ordered classification method with the combination of spectral, texture, and shape information performed better than conventional methods.