This paper presents a new method for salient object detection based on a sophisticated appearance comparison of multisize superpixels. Those superpixels are modeled by multivariate normal distributions in CIE-Lab color space, which are estimated from the pixels they comprise. This fitting facilitates an efficient application of the Wasserstein distance on the Euclidean norm ( [Formula: see text]) to measure perceptual similarity between elements. Saliency is computed in two ways. On the one hand, we compute global saliency by probabilistically grouping visually similar superpixels into clusters and rate their compactness. On the other hand, we use the same distance measure to determine local center-surround contrasts between superpixels. Then, an innovative locally constrained random walk technique that considers local similarity between elements balances the saliency ratings inside probable objects and background. The results of our experiments show the robustness and efficiency of our approach against 11 recently published state-of-the-art saliency detection methods on five widely used benchmark data sets.

The hypothalamic paraventricular nucleus (PVN) is critically involved in elevated sympathetic output and the development of hypertension. However, changes in group I metabotropic glutamate receptors (mGluR1 and mGluR5) and their relevance to the hyperactivity of PVN presympathetic neurons in hypertension remain unclear. Here, we found that selectively blocking mGluR5 significantly reduced the basal firing activity of spinally projecting PVN neurons in spontaneously hypertensive rats (SHRs), but not in normotensive WistarKyoto (WKY) rats. However, blocking mGluR1 had no effect on the firing activity of PVN neurons in either group. The mRNA and protein levels of mGluR5 in the PVN and rostral ventrolateral medulla were significantly higher in SHRs than in WKY rats. The group I mGluR selective agonist (S)-3,5-dihydroxyphenylglycine (DHPG) similarly increased the firing activity of PVN neurons in WKY rats and SHRs. In addition, blocking NMDA receptors (NMDARs) through bath application or intracellular dialysis not only decreased the basal firing in SHRs, but also eliminated DHPG-induced excitation of spinally projecting PVN neurons. DHPG significantly increased the amplitude of NMDAR currents without changing their decay kinetics. Interestingly, DHPG still increased the amplitude of NMDAR currents and caused reappearance of functional NMDAR channels after initially blocking NMDARs. In addition, protein kinase C (PKC) inhibition or intracellular dialysis with synaptosomal-associated protein of 25 kDa (SNAP-25)-blocking peptide abolished DHPG-induced increases in NMDAR currents of PVN neurons in SHRs. Our findings suggest that mGluR5 in the PVN is upregulated in hypertension and contributes to the hyperactivity of PVN presympathetic neurons through PKC-and SNAP-25-mediated surface expression of NMDARs.

An improved dehazing algorithm based on dark channel theory is proposed, in order to solve the problems of colour distortion and halo effect which still exists in dark channel prior algorithm. The dark channel prior theory may lead to colour distortion in sky region. Firstly, the guided filter is used to refine the segmentation of the sky region, and the atmospheric light is estimated accurately. Then, the median filter is used to obtain the detailed edge information. So a more clear transmission can be gotten which effectively suppress the halo problem. Finally, the gamma correction is applied to enhance image lightness with an empirically selected gamma parameter. The experimental results show that the proposed algorithm can effectively remove the haze. It can correct the colour distortion of the sky area and eliminate the halo effect at the edge of the scene.

In this paper, a novel Multiview CLOUD (mCLOUD) visual feature extraction mechanism is proposed for the task of categorizing clouds based on ground-based images. To completely characterize the different types of clouds, mCLOUD first extracts the raw visual descriptors from the views of texture, structure, and color simultaneously, in a densely sampled way-specifically, the scale invariant feature transform (SIFT), the census transform histogram (CENTRIST), and the statistical color features are extracted, respectively. To obtain a more descriptive cloud representation, the feature encoding of the raw descriptors is realized by using the Fisher vector. This is followed by the feature aggregation procedure. A linear support vector machine (SVM) is employed as the classifier to yield the final cloud image categorization result. The experiments on a challenging cloud dataset termed the six-class Huazhong University of Science and Technology (HUST) cloud demonstrate that mCLOUD consistently outperforms the state-of-the-art cloud classification approaches by large margins (at least 6.9%) under all the different experimental settings. It has also been verified that, compared to the single view, the multiview cloud representation generally enhances the performance.

Conventional deconvolution methods assume that the microscopy system is spatially invariant, introducing considerable errors. We developed a method to more precisely estimate space-variant point-spread functions from sparse measurements. To this end, a space-variant version of deblurring algorithm was developed and combined with a total-variation regularization. Validation with both simulation and real data showed that our PSF model is more accurate than the piecewise-invariant model and the blending model. Comparing with the orthogonal basis decomposition based PSF model, our proposed model also performed with a considerable improvement. We also evaluated the proposed deblurring algorithm. Our new deblurring algorithm showed a significantly better signal-to-noise ratio and higher image quality than those of the conventional space-invariant algorithm.

No abstract

Sensitivity-encoded spectroscopic imaging (SENSE-SI) reduces scanning time by using multiple coils for parallel signal acquisition. Significant artifacts could be induced by SENSE-SI, mainly due to the low-resolution nature of spectroscopic imaging. The present study introduces a novel method to reduce the artifacts. High-resolution sensitivity maps are used in low-resolution SENSE reconstruction.

No abstract