Hongxia Hao

Hierarchical semantic model and scattering mechanism based PolSAR image classification

For polarimetric SAR (PolSAR) image classification, it is a challenge to classify the aggregated terrain types, such as the urban area, into semantic homogenous regions due to sharp bright-dark variations in intensity. The aggregated terrain type is formulated by the similar ground objects aggregated together. In this paper, a polarimetric hierarchical semantic model (PHSM) is firstly proposed to overcome this disadvantage based on the constructions of a primal-level and a middle-level semantic. The primal-level semantic is a polarimetric sketch map which consists of sketch segments as the sparse representation of a PolSAR image. The middle-level semantic is a region map which can extract semantic homogenous regions from the sketch map by exploiting the topological structure of sketch segments. Mapping the region map to the PolSAR image, a complex PolSAR scene is partitioned into aggregated, structural and homogenous pixel-level subspaces with the characteristics of relatively coherent terrain types in each subspace. Then, according to the characteristics of three subspaces above, three specific methods are adopted, and furthermore polarimetric information is exploited to improve the segmentation result. Experimental results on PolSAR data sets with different bands and sensors demonstrate that the proposed method is superior to the state-of-the-art methods in region homogeneity and edge preservation for terrain classification.

Pan-sharpening algorithm to remove thin cloud via mask dodging and nonsampled shift-invariant shearlet transform

Abstract The goal of pan-sharpening is to get an image with higher spatial resolution and better spectral information. However, the resolution of the pan-sharpened image is seriously affected by the thin clouds. For a single image, filtering algorithms are widely used to remove clouds. These kinds of methods can remove clouds effectively, but the detail lost in the cloud removal image is also serious. To solve this problem, a pan-sharpening algorithm to remove thin cloud via mask dodging and nonsampled shift-invariant shearlet transform (NSST) is proposed. For the low-resolution multispectral (LR MS) and high-resolution panchromatic images with thin clouds, a mask dodging method is used to remove clouds. For the cloud removal LR MS image, an adaptive principal component analysis transform is proposed to balance the spectral information and spatial resolution in the pan-sharpened image. Since the clouds removal process causes the detail loss problem, a weight matrix is designed to enhance the details of the cloud regions in the pan-sharpening process, but noncloud regions remain unchanged. And the details of the image are obtained by NSST. Experimental results over visible and evaluation metrics demonstrate that the proposed method can keep better spectral information and spatial resolution, especially for the images with thin clouds.

A Novel Image Representation Framework Based on Gaussian Model and Evolutionary Optimization

We propose a novel image representation framework based on Gaussian model and evolutionary optimization (EO). In this framework, image patches are categorized into smooth and nonsmooth ones, and the two categories are treated distinctively. For a smooth patch, we formulate it as the summation of a direct component and a variation component (VC). We observe that the values of all VCs in an image can be well fitted by a Gaussian distribution, according to which we present an efficient reconstruction approach based on maximizing the logarithm a posteriori probability. For a nonsmooth patch, we introduce the mechanism of EO to solve a combinatorial optimization over a principal component analysis dictionary. In addition, we develop two approaches for estimating the coefficients of the atoms. Experiment results demonstrate that the proposed framework obtains the state-of-the-art results in several image inverse problems.

A group matching pursuit for image reconstruction

Matching Pursuit (MP) is a fast and effective sparse representation algorithm, so it and its improved algorithms are used to solve the problem of Compressive Sensing (CS) reconstruction. MP finds the support of the unknown signal sequentially based on the correlation values between the basis vectors and the measurement vector. As the sampling rate decreases, the signal could not be reconstructed successfully. The nature image wavelet coefficients always remain a residual dependency structure which we can use to improve the CS reconstruction, such as an aggregation of neighborhood and the significant coefficients appear at the locations of the image edges. Make full use of the priors are mentioned above, we propose a Group Matching Pursuit (GMP) algorithm base on the edge. In GMP, with the neighborhood structure employed as a spatial constraint, the coefficients are organized as groups to restrain each other. Then the extracted image edge is used as the prior information to improve the reconstruction quality. Finally, we propose a Bayesian Group Matching Pursuit (BGMP) algorithm. In BGMP the group coefficients are modeled by a multivariate Gaussian distribution, and solved by a maximum a posteriori probability (MAP) estimate. Experiments have shown that, the methods based on GMP have a better reconstruction in solving the reconstruction problem of CS. GMP improved the reconstruction result with the aggregation of the wavelet domain.With the group correlation value, GMP can accurately locate the position of large coefficients.The estimated image edge is used to guide the locations of significant coefficients.The group coefficients are modeled by a multivariate Gaussian distribution and solved by MAP estimate.

Unsupervised polarimetric synthetic aperture radar image classification based on sketch map and adaptive Markov random field

Abstract. Markov random field (MRF) model is an effective tool for polarimetric synthetic aperture radar (PolSAR) image classification. However, due to the lack of suitable contextual information in conventional MRF methods, there is usually a contradiction between edge preservation and region homogeneity in the classification result. To preserve edge details and obtain homogeneous regions simultaneously, an adaptive MRF framework is proposed based on a polarimetric sketch map. The polarimetric sketch map can provide the edge positions and edge directions in detail, which can guide the selection of neighborhood structures. Specifically, the polarimetric sketch map is extracted to partition a PolSAR image into structural and nonstructural parts, and then adaptive neighborhoods are learned for two parts. For structural areas, geometric weighted neighborhood structures are constructed to preserve image details. For nonstructural areas, the maximum homogeneous regions are obtained to improve the region homogeneity. Experiments are taken on both the simulated and real PolSAR data, and the experimental results illustrate that the proposed method can obtain better performance on both region homogeneity and edge preservation than the state-of-the-art methods.

A Nonlocal Means for Speckle Reduction of SAR Image With Multiscale-Fusion-Based Steerable Kernel Function

For the robustness of a patch-based metric, the nonlocal means method is widely applied for speckle reduction of synthetic aperture radar (SAR) images, where the similarity computed by the patch-based metric is used as weight, and weighted averaging is used to obtain the true value. However, not knowing the local spatial property, a fixed kernel (e.g., Gaussian kernel or uniform kernel) is always used to compute the weight. This is not good for the preservation of geometrical features (e.g., edges, lines, and points). In this letter, considering the characteristics of SAR imagery, a multiscale-fusion-based steerable kernel function was formed to explore the local spatial property of SAR images. In addition, by combining the kernel function with a ratio-based similarity metric designed with the distribution of the speckles ratio, a new patch-based metric was formed and used with the nonlocal scheme for speckle reduction. In the experiments, by comparing with two state-of-the-art methods, a reasonable performance was obtained by our method, in terms of speckle reduction and detail preservation.

The Overcomplete Dictionary-Based Directional Estimation Model and Nonconvex Reconstruction Methods

In this paper, it is proposed the directional estimation model on the overcomplete dictionary, which bridges the compressed measurements of the image blocks and the directional structures of the dictionary. In the model, it is established the analytical method to estimate the structure type of a block as either smooth, single-oriented, or multioriented. Furthermore, the structures of each type of blocks are described by the structured subdictionaries. Then based on the obtained estimations and the constrains on the sparse dictionaries, the original image will be estimated. To verify the model, the nonconvex methods are designed for compressed sensing. Specifically, the greedy pursuit-based methods are established to search the subdictionaries obtained by the model, which achieve better local structural estimation than the methods without the directional estimation. More importantly, it is proposed the nonconvex image reconstruction method with direction-guided dictionaries and evolutionary searching strategies (NR_DG), where the evolutionary searching strategies are delicately designed for each type of the blocks based on the directional estimation. By the experimental results, it is shown that the NR_DG method performs better than the available two-stage evolutionary reconstruction method.

Image Enhancement based on intrascale dependencies of the Second Generation Curvelet Transform

This paper presents a strong noise image enhancement method based on intrascale dependencies of the second generation curvelet transform. Observing that the immediate four neighbor coefficients bear the most important dependencies, we use spatial clustering property of the intrascale neighbor coefficients to separate noise and signal of interest, and to deal with them differently, i.e. to suppress noise and strengthen edges. Comparing our approach with Starcks enhancement model (Starck et al., 2003), we experimentally find that for high noise level images, our method outperforms the starcks system in noise suppression and signal strengthening and produces better enhancement results.