Using local transition probability models in Markov Random Field for multi-temporal image classification

Making use full of multi-source and multi-temporal information to extract richer and interesting information is a tendency in analysis of remote sensing images. In this paper, spatial and temporal contextual classification based on Markov Random Field (MRF) is used to classify ecological function vegetation in Poyang Lake. The results show that spatial and temporal neighborhood complementary information from different images can be used to remove the spectral confusion of different kinds of vegetation on single image and improve classification accuracy compared to MLC method. The local transition model is more accurate than global transition model and also effective in computation. Building effective spatial and temporal neighborhood model for information extraction in special application is the key of multi-source and multi-temporal image analysis. Although spatial and temporal contextual classification method is computation demanding, it's promising in the application emphasizing classification accuracy.