High resolution satellite imagery segmentation based on adaptively integrated multiple features

Automatic segmentation of high resolution satellite (HRS) imagery is the first step and a very important part of object-oriented approaches. The HRS sensors increase the spectral within-field heterogeneity and the structural or spatial details of images. Spatial features are important to HRS image analysis in addition to spectral information. This paper presents a novel feature extraction method and evaluates its performance on segmentation of HRS images based on adaptively integrating multiple features. The first two principal component (PC) images are obtained by principal component analysis (PCA) of a multispectral image and used to calculate the texture and spectral distributions of a region, which are denoted by two-dimensional (2D) histograms. The 2D texture histogram of a region is the joint distribution of its two texture labeled images calculated by rotation invariant local binary pattern (LBP) operator. The spectral distribution of a region is the joint distribution of the pixel values of its two PC images after normalization. The color feature is a 2D hue/saturation histogram that is computed through IHLS color space. The three features are integrated by a weighted sum similarity measure and used to hierarchical splitting, modified agglomerative merging and boundary refinement segmentation framework. The segmentation scheme based on adaptively integrating multiple features demonstrates promising results.