A novel segmentation method of high resolution remote sensing image based on multi-feature object-oriented Markov random fields model

A novel methodology base on multi-feature object-oriented MRF(MFOMRF) is proposed in order to obtain precise segmentation of high resolution satellite image. Conventional pixel-by-pixel MRF model methods only consider spatial correlation and texture of each pixel fixed square neighborhood, which are not satisfactory as the high resolution satellite contains complex spatial and texture information. the segmentation method of high resolution remote sensing image based on pixel-by-pixel MRF model usually suffer from salt and pepper noise. Based on the analysis of problems existing in pixel-by-pixel MRF model methods of high-resolution remote sensed images, an multi-feature object-oriented MRF-based segmentation algorithm is proposed. The proposed method is made up of two blocks: (1) Mean-Shift algorithm is employed to obtain the over-segmentation results and the primary processing units are generated, based on which the object adjacent graph (OAG) can be constructed. (2) The generation of objects by overly segmented, the spectral, textural, and shape feature are extracted for each node in the OAG, all of these features are constructed in a feature vector, based on which the feature model is defined on the OAG, and the neighbor system, potential cliques and energy functions of OAG are exploited in the labeling model. The proposed segmentation method is evaluated on high resolution remote sensed image data set-GeoEye, And the experimental results verified that MFOMRF has the capability to obtain better segmentation results, especially for textural and shape richer images.