The invention discloses a
fast algorithm for judging the contaminated area of Bohai Bay based on
remote sensing images: based on a Bayesian model, an
Ising model and a
signal model, the Bayesian-Isin-
Signal (BIS)
hybrid model is constructed; the variational Bayesian method is used to estimate the background low rank matrix L: to estimate U and V, to estimate the super parameter alpha, and to estimate the
noise precision beta, and estimate foreground
support matrix S. The invention aims at the judgment problem of Bohai Bay contaminated area of
remote sensing image, restricts the form of matrixdecomposition by low rank condition and introduces continuous prior as sparse condition constraint to achieve the purpose of simultaneously estimating low rank matrix of background and foreground
support matrix. In order to guarantee the existence of low rank solutions in the low rank
decomposition process, an independent prior distribution with the same sparse profile is introduced for variablesand parameters, and a posteriori
inference is made by using variational Bayesian method. In addition, considering the
spatial distribution characteristics of
singular value space, Markov random fieldsare introduced to estimate the foreground
support matrix.