Maximum a posteriori estimation

About: Maximum a posteriori estimation is a research topic. Over the lifetime, 7486 publications have been published within this topic receiving 222291 citations. The topic is also known as: Maximum a posteriori, MAP & maximum a posteriori probability.

An iterative approach to multisensor sea ice classification

Abstract: Characterizing the variability in sea ice in the polar regions is fundamental to an understanding of global climate and the geophysical processes governing climate changes. Sea ice can be grouped into a number of general classes with different characteristics. Multisensor data from NSCAT, ERS-2, and SSM/I are reconstructed into enhanced resolution imagery for use in ice-type classification. The resulting twelve-dimensional data set is linearly transformed through principal component analysis to reduce data dimensionality and noise levels. An iterative statistical data segmentation algorithm is developed using maximum likelihood (ML) and maximum a posteriori (MAP) techniques. For a given ice type, the conditional probability distributions of observed vectors are assumed to be Gaussian. The cluster centroids, covariance matrices, and a priori distributions are estimated from the classification of a previous temporal image set. An initial classification is produced using centroid training data and a weighted nearest-neighbor classifier. Though validation is limited, the algorithm results in an ice classification that is judged to be superior to a conventional k-means approach.

MAP estimation of semi-metric MRFs via hierarchical graph cuts

Abstract: We consider the task of obtaining the maximum a posteriori estimate of discrete pairwise random fields with arbitrary unary potentials and semi-metric pairwise potentials. For this problem, we propose an accurate hierarchical move making strategy where each move is computed efficiently by solving an st-MINCUT problem. Unlike previous move making approaches, e.g. the widely used α-expansion algorithm, our method obtains the guarantees of the standard linear programming (LP) relaxation for the important special case of metric labeling. Unlike the existing LP relaxation solvers, e.g. interior-point algorithms or tree-reweighted message passing, our method is significantly faster as it uses only the efficient st-MINCUT algorithm in its design. Using both synthetic and real data experiments, we show that our technique outperforms several commonly used algorithms.

Performance evaluation for MAP state estimate fusion

Abstract: This paper presents a quantitative performance evaluation method for the maximum a posteriori (MAP) state estimate fusion algorithm. Under ideal conditions where data association is assumed to be perfect, it has been shown that the MAP or best linear unbiased estimate (BLUE) fusion formula provides the best linear minimum mean squared estimate (LMMSE) given local estimates under the linear Gaussian assumption for a static system. However, for a dynamic system where fusion is recursively performed by the fusion center on local estimates generated from local measurements, it is not obvious how the MAP algorithm will perform. In the past, several performance evaluation methods have been proposed for various fusion algorithms, including simple convex combination, cross-covariance combination, information matrix, and MAP fusion. However, not much has been done to quantify the steady state behavior of these fusion methods for a dynamic system. The goal of this work is to present analytical fusion performance results for MAP state estimate fusion without extensive Monte Carlo simulations, using an approach developed for steady state performance evaluation for track fusion. Two different communication strategies are considered: fusion with and without feedback to the sensors. Analytic curves for the steady state performance of the fusion algorithm for various communication patterns are presented under different operating conditions.