A contextual classification scheme based on MRF model with improved parameter estimation and multiscale fuzzy line process

A Markov random field (MRF) based method using both contextual information and multiscale fuzzy line process for classifying remotely sensed imagery is detailed in this paper. The study area known as Elkhorn Slough is an important natural reserve park located in the central California coast, USA. Satellite imagery such as IKONOS panchromatic and multispectral data provides a convenient way for supporting the monitoring process around this area. Within the proposed classification mechanism, the panchromatic image, benefited from its high resolution, mainly serves for extracting multiscale line features by means of wavelet transform techniques. The resulting multiscale line features are merged through a fuzzy fusion process and then incorporated into the MRF model accompanied with multispectral imagery to perform contextual classification so as to restrict the over-smooth classification patterns and reduce the bias commonly contributed by those boundary pixels. The MRF model parameter is estimated based on the probability histogram analysis to those boundary pixels, and the algorithm called maximum a posterior margin (MPM) is applied to search the solution. The results show that the proposed method, based on the MRF model with the multiscale fuzzy line process, successfully generates the patch-wise classification patterns, and simultaneously improved the accuracy and visual interpretation.