Point set registration plays an important role in computer vision and pattern recognition. In this article, we propose an adaptive hierarchical probabilistic model (HPM) under a variational Bayesian (VB) framework for point set registration problem. The main contributions of this article are given as follows. First, a dynamic putative inlier estimation strategy is proposed through the hesitant fuzzy Einstein weighted averaging based membership calculation and component estimation using symmetric cross entropy. Second, a student-t mixture model based HPM is designed to solve outlier and occlusion problems during registration. Third, a VB-based transformation updating is proposed to construct a robust and adjustable transformation for effectively fitting target point set while further resisting outliers. The performances of the proposed method in point set and image registrations against 11 state-of-the-art methods are evaluated, in which our method gives the best performance in most scenarios.

In this work, we propose a hierarchical Bayesian network based point set registration method to solve missing correspondences and various massive outliers. We construct this network first using the finite Student s t latent mixture model (TLMM), in which distributions of latent variables are estimated by a tree-structured variational inference (VI) so that to obtain a tighter lower bound under the Bayesian framework. We then divide the TLMM into two different mixtures with isotropic and anisotropic covariances for correspondences recovering and outliers identification, respectively. Finally, the parameters of mixing proportion and covariances are both taken as latent variables, which benefits explaining of missing correspondences and heteroscedastic outliers. In addition, a cooling schedule is adopted to anneal prior on covariances and scale variables within designed two phases of transformation, it anneal priors on global and local variables to perform a coarse-to- fine registration. In experiments, our method outperforms five state-of-the-art methods in synthetic point set and realistic imaging registrations.

Two-dimensional phase unwrapping is a key step in the phase extraction process, an image-processing stage that is common to many different systems. Many varied approaches have been proposed over the past several decades. However, with the growth of image scale, it poses new challenges in terms of computational and memory requirements to phase unwrapping that require a global approach to obtain good results. Owing to only a single process used in most previous algorithm implementations, it becomes more problematic to unwrapping when the required computing resources exceed the capability of one computer. Meanwhile, with the development and application of supercomputer techniques, high-performance computing is emerging as a promising platform for scientific applications. In this paper, a novel hybrid multiprocessing and multithreading algorithm is proposed in order to overcome the problem of unwrapping large data sets. In this algorithm, we improve on Goldstein's branch-cut algorithm using simulated annealing idea to further optimize the set of branch cuts in parallel. For large data sets, the tiling strategy based on the nature of parallel computing guarantees the globality of phase unwrapping and avoids large-scale errors introduced. Using real and simulated interferometric data, we demonstrate that our algorithms are highly competitive with other existing algorithms in speed and accuracy. We also demonstrate that the proposed algorithm can be efficiently parallelized and performed across nodes in a high-performance computing cluster.

An algorithm for retrieval of surface net radiation with Landsat TM/ETM+ data was developed in two parts in this study. First of all, net short wave radiation was computed with an improved algorithm for atmospheric correction based on dark object scheme associated with topographic information of the target site to account for the topographic affect on radiant regimes, and then a thermal radiant transfer model for accurate estimation of net long wave radiation over mountainous region by using surface temperature derived from the extended mono-window algorithm to integrate with surface energy balance equations was established. The thermal radiation from surrounding surface thus can be estimated, and atmospheric downward long wave radiation was calculated by means of an empirical formula related to surface temperature. With these two terms, Pixel based surface net radiation can be obtained. An evident advantage of this model is that only two atmospheric parameters, i.e. atmospheric mean effective temperature and surface temperature, are needed.The proposed approach was experimentally applied to a mountainous region located in the Hanjiang Basin, south western China. 6S code was utilized to the Landsat ETM+ image acquired over the region to simulate the surface and atmospheric radiative parameters under different geographic zones at selected climatic conditions to examine the performance of the proposed model. It was suggested that the maximum error in albedo extraction by the proposed algorithm is about 17% with mean error less than 10%, the maximum error in retrieved short wave net radiation and long wave net radiation is about 15% and 12% with mean error less than about 11% and 9% respectively, which suggested the proposed approach an valid and operational mean in quantitative reversion of surface long wave radiation with satisfied accuracy.

An algorithm based on a BP neural network for retrieval of near-surface daily mean, maximum and minimum air temperature from remotely sensed data was developed in this paper. The algorithm was tested to map air temperature by integrating Landsat Enhanced Thematic Mapper Plus (ETM+) derived surface information with GIS provided meteorological parameters with a BP neural network over the upstream Basin of the Hanjiang River, Southwestern China. The parameters involved in the training of the BP neural network for inversion of air temperature can be subdivided into six groups, each was used to represent different data sources for testing the sensitivity of these variables on the near-surface air temperature retrieved. These parameters are remotely sensed albedo, NDVI, layered meteorological data of station observed daily mean, maximum and minimum are temperature provided by GIS as well as the DEM of the study site. Five criterions, namely Mean Error (ME), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Relative Error (MRE) and correlation coefficient (R2) were utilized to evaluate the performance of the proposed algorithm by comparing the retrieved and the observed air temperature quantitatively. Systematic analyses suggested that the satisfied retrieval of daily mean and maximum near-surface air temperature can be achieved with MRE of 3.02% and 2.23% and RMSE of 0.93□ and 0.9□ respectively. However, only when all the parameters including daily mean and maximum nearsurface air temperature were used for training the BP neural network, the daily minimum air temperature could be retrieved with the best MRE of 8.31%. From this study, it can be concluded that the BP neural network integrating with surface meteorological observations might be a promising approach for retrieving near-surface air temperature with reliable accuracy.