Remote sensing image registration plays a significant role in various fields such as disaster monitoring, response, agriculture and forestry management. Registration of remote sensing images is more complicated than natural images due to the larger coverage area and being affected by factors such as the atmosphere, clouds, and sensor noise. To address the limitations of the SuperPoint method commonly used for natural image registration in adapting to large lighting variations or repetitive patterns, this paper introduces a lightweight network to enhance the keypoint descriptors in SuperPoint. The network takes the original descriptors and geometric properties of keypoints as inputs and employs a descriptor enhancement stage and a spatial context enhancement stage to enhance the descriptors. The results indicate that, compared with the SuperPoint approach, the method we optimized shows better performance when tested on Landsat-7 and WorldView-3 images captured at different time periods.

Tree-based algorithms for spatial domain applications scale poorly in the distributed setting without extensive experimentation and optimization. Reusability via well-designed parallel abstractions supported by efficient parallel algorithms is therefore desirable. We present ParaTreeT, a parallel tree toolkit for state-of-the-art performance and programmer productivity. ParaTreeT leverages a novel shared-memory software cache to reduce communication volume and idle time throughout traversal. By dividing particles and subtrees across processors independently, it improves decomposition and limits synchro-nization during tree build. Tree-node states are extracted from the particle set with the Data abstraction, and traversal work and pruning are defined by the Visitor abstraction. ParaTreeT provides built-in trees, decompositions, and traversals that offer application-specific customization. We demonstrate ParaTreeT's improved computational performance over even specialized codes with multiple applications on CPUs. We evaluate how several applications derive benefit from ParaTreeT's models while pro-viding new insights to these workloads through experimentation.

Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution. For multidimensional and non-binary data, it is necessary to vectorize and discretize the information in order to apply the conventional RBM. It is well-known that vectorization would destroy internal structure of data, and the binary units will limit the applying performance due to fickle real data. To address these issues, this paper proposes a Matrix variate Gaussian Restricted Boltzmann Machine (MVGRBM) model for matrix data whose entries follow Gaussian distributions. Compared with some other RBM algorithms, MVGRBM can model real value data better and it has good performance in image classification. To prove that adding Gaussian parameters could model input data well, we compared the reconstruction performance of the Gaussian parameters updating and fixed.

The probabilistic principal component analysis (PPCA) is built upon a global linear mapping, with which it is insufficient to model complex data variation. This paper proposes a mixture of bilateral-projection probabilistic principal component analysis model (mixB2DPPCA) on 2D data. With multi-components in the mixture, this model can be seen as a 'soft' cluster algorithm and has capability of modeling data with complex structures. A Bayesian inference scheme has been proposed based on the variational EM (Expectation-Maximization) approach for learning model parameters. Experiments on some publicly available databases show that the performance of mixB2DPPCA has been largely improved, resulting in more accurate reconstruction errors and recognition rates than the existing PCA-based algorithms.