arXiv subjects

Qian Zhao

Publications and source records attributed to Qian Zhao.

At least 145 records · Page 8Linked to original sources

arXiv2019

A Survey on Rain Removal from Video and Single Image

Rain streaks might severely degenerate the performance of video/image processing tasks. The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years. However, there is still not a comprehensive survey paper to summarize current rain removal methods and fairly compare their generalization performance, and especially, still not a off-the-shelf toolkit to accumulate recent representative methods for easy performance comparison and capability evaluation. Aiming at this meaningful task, in this study we present a comprehensive review for current rain removal methods for video and a single image. Specifically, these methods are categorized into model-driven and data-driven approaches, and more elaborate branches of each approach are further introduced. Intrinsic capabilities, especially generalization, of representative state-of-the-art methods of each approach have been evaluated and analyzed by experiments implemented on synthetic and real data both visually and quantitatively. Furthermore, we release a comprehensive repository, including direct links to 74 rain removal papers, source codes of 9 methods for video rain removal and 20 ones for single image rain removal, 19 related project pages, 6 synthetic datasets and 4 real ones, and 4 commonly used image quality metrics, to facilitate reproduction and performance comparison of current existing methods for general users. Some limitations and research issues worthy to be further investigated have also been discussed for future research of this direction.

eess.IV↗

arXiv2019

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from training loss to sample weight, and then iterating between weight recalculating and classifier updating. Current approaches, however, need manually pre-specify the weighting function as well as its additional hyper-parameters. It makes them fairly hard to be generally applied in practice due to the significant variation of proper weighting schemes relying on the investigated problem and training data. To address this issue, we propose a method capable of adaptively learning an explicit weighting function directly from data. The weighting function is an MLP with one hidden layer, constituting a universal approximator to almost any continuous functions, making the method able to fit a wide range of weighting functions including those assumed in conventional research. Guided by a small amount of unbiased meta-data, the parameters of the weighting function can be finely updated simultaneously with the learning process of the classifiers. Synthetic and real experiments substantiate the capability of our method for achieving proper weighting functions in class imbalance and noisy label cases, fully complying with the common settings in traditional methods, and more complicated scenarios beyond conventional cases. This naturally leads to its better accuracy than other state-of-the-art methods.

cs.LG↗

arXiv2019

Video Rain/Snow Removal by Transformed Online Multiscale Convolutional Sparse Coding

Video rain/snow removal from surveillance videos is an important task in the computer vision community since rain/snow existed in videos can severely degenerate the performance of many surveillance system. Various methods have been investigated extensively, but most only consider consistent rain/snow under stable background scenes. Rain/snow captured from practical surveillance camera, however, is always highly dynamic in time with the background scene transformed occasionally. To this issue, this paper proposes a novel rain/snow removal approach, which fully considers dynamic statistics of both rain/snow and background scenes taken from a video sequence. Specifically, the rain/snow is encoded as an online multi-scale convolutional sparse coding (OMS-CSC) model, which not only finely delivers the sparse scattering and multi-scale shapes of real rain/snow, but also well encodes their temporally dynamic configurations by real-time ameliorated parameters in the model. Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence. The approach so constructed can naturally better adapt to the dynamic rain/snow as well as background changes, and also suitable to deal with the streaming video attributed its online learning mode. The proposed model is formulated in a concise maximum a posterior (MAP) framework and is readily solved by the ADMM algorithm. Compared with the state-of-the-art online and offline video rain/snow removal methods, the proposed method achieves better performance on synthetic and real videos datasets both visually and quantitatively. Specifically, our method can be implemented in relatively high efficiency, showing its potential to real-time video rain/snow removal.

cs.CV↗

arXiv2019

Shear-wave manipulation by embedded soft devices

Hyperelastic transformation theory has proven shear-wave manipulation devices with various functions can be designed by utilizing neo-Hookean material with appropriate pre-deformation. However, it is still elusive that how can such devices match with the background medium in which they embedded. In this work, we present a systematic formulation of the transmission and reflection of elastic waves at the interface between un-deformed and pre-deformed hyperelastic materials. With the combination of theoretical analyses and numerical simulations, we specifically investigate the shear-wave propagation from an un-deformed neo-Hookean material to the one subject to different homogeneous deformations. Among three typical deformation modes, we found "constrained" uniaxial tension and simple shear guarantee total transmission, whereas "ordinary" uniaxial tension and hydrostatic compression cause wave reflection. On this basis, three embedded shear-wave manipulation devices, including a unidirectional cloak, a splicable beam bend, and a concave lens, are proposed and verified through numerical simulations. This work may pave the way for the design and realization of soft-matter-based wave control devices. Potential applications can be anticipated in nondestructive testing, structure impact protection, biomedical imaging, and soft robotics.

cond-mat.soft↗

arXiv2019

Custom Edge-Element FEM Solver and its Application to Eddy-Current Simulation of Realistic 2M-Element Human Brain Phantom

Extensive research papers of three-dimensional computational techniques are widely used for the investigation of human brain pathophysiology. Eddy current analyzing could provide an indication of conductivity change within a biological body. A significant obstacle to current trend analyses is the development of a numerically stable and efficiency-finite element scheme that performs well at low frequency and does not require a large number of degrees of freedom. Here, a custom finite element method (FEM) solver based on edge elements is proposed using the weakly coupled theory, which separates the solution into two steps. First, the background field (the magnetic vector potential on each edge) is calculated and stored. Then, the electric scalar potential on each node is obtained by FEM based on Galerkin formulations. Consequently, the electric field and eddy current distribution in the object can be obtained. This solver is more efficient than typical commercial solvers since it reduces the vector eddy current equation to a scalar one, and reduces the meshing domain to just the eddy current region. It can therefore tackle complex eddy current calculations for models with much larger numbers of elements, such as those encountered in eddy current computation in biological tissues. An example is presented with a realistic human brain mesh of 2 million elements. In addition, with this solver, the equivalent magnetic field induced from the excitation coil is applied, and therefore there is no need to mesh the excitation coil. In combination, these significantly increase the efficiency of the solver.

physics.med-ph↗

arXiv2019

An equivalent-effect phenomenon in eddy current non-destructive testing of thin structures

The inductance/impedance due to thin metallic structures in non-destructive testing (NDT) is difficult to evaluate. In particular, in Finite Element Method (FEM) eddy current simulation, an extremely fine mesh is required to accurately simulate skin effects especially at high frequencies, and this could cause an extremely large total mesh for the whole problem, i.e. including, for example, other surrounding structures and excitation sources like coils. Consequently, intensive computation requirements are needed. In this paper, an equivalent-effect phenomenon is found, which has revealed that alternative structures can produce the same effect on the sensor response, i.e. mutual impedance/inductance of coupled coils if a relationship (reciprocal relationship) between the electrical conductivity and the thickness of the structure is observed. By using this relationship, the mutual inductance/impedance can be calculated from the equivalent structures with much fewer mesh elements, which can significantly save the computation time. In eddy current NDT, coils inductance/impedance is normally used as a critical parameter for various industrial applications, such as flaw detection, coating and microstructure sensing. Theoretical derivation, measurements and simulations have been presented to verify the feasibility of the proposed phenomenon.

eess.SP↗

arXiv2019

Measurement of permeability for ferrous metallic plates using a novel lift-off compensation technique on phase signature

Lift-off of sensor affects the prediction of electromagnetic properties for both ferrous and non-ferrous steel plates. In this paper, we developed a strategy to address this issue for ferrous plates. With increased lift-off, the phase of the measured impedance for steel plates reduces. Meanwhile, the magnitude of the impedance signal decreases. Based on these facts, a phase compensation algorithm is developed which corrects the phase change due to lift-off considering the magnitude of the impedance signal. Further, a new magnetic permeability prediction technique is presented, which has been validated by analytical and measured results. With this new technique, the error in permeability prediction is less than 2% within the range of lift-offs tested.

eess.SP↗

arXiv2019

Semi-supervised Transfer Learning for Image Rain Removal

Single image rain removal is a typical inverse problem in computer vision. The deep learning technique has been verified to be effective for this task and achieved state-of-the-art performance. However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data. To this issue, this paper firstly proposes a semi-supervised learning paradigm toward this task. Different from traditional deep learning methods which only use supervised image pairs with/without synthesized rain, we further put real rainy images, without need of their clean ones, into the network training process. This is realized by elaborately formulating the residual between an input rainy image and its expected network output (clear image without rain) as a specific parametrized rain streaks distribution. The network is therefore trained to adapt real unsupervised diverse rain types through transferring from the supervised synthesized rain, and thus both the short-of-training-sample and bias-to-supervised-sample issues can be evidently alleviated. Experiments on synthetic and real data verify the superiority of our model compared to the state-of-the-arts.

cs.CV↗

arXiv2019

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

Hyperspectral imaging can help better understand the characteristics of different materials, compared with traditional image systems. However, only high-resolution multispectral (HrMS) and low-resolution hyperspectral (LrHS) images can generally be captured at video rate in practice. In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image. In specific, we construct a novel MS/HS fusion model which takes the observation models of low-resolution images and the low-rankness knowledge along the spectral mode of HrHS image into consideration. Then we design an iterative algorithm to solve the model by exploiting the proximal gradient method. And then, by unfolding the designed algorithm, we construct a deep network, called MS/HS Fusion Net, with learning the proximal operators and model parameters by convolutional neural networks. Experimental results on simulated and real data substantiate the superiority of our method both visually and quantitatively as compared with state-of-the-art methods along this line of research.

cs.CV↗

arXiv2018

Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing

The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks. This term is calculated by assuming identical and independent sparsity structures on all bands of gradient maps calculated along spatial and spectral HSI modes. This, however, is always largely deviated from the real cases, where the gradient maps are generally with different while correlated sparsity structures across all their bands. Such deviation tends to hamper the performance of the related method by adopting such prior term. To this is- sue, this paper proposes an enhanced 3DTV (E-3DTV) regularization term beyond conventional 3DTV. Instead of imposing sparsity on gradient maps themselves, the new term calculated sparsity on the subspace bases on the gradient maps along their bands, which naturally encode the correlation and difference across these bands, and more faithfully reflect the insightful configurations of an HSI. The E-3DTV term can easily replace the previous 3DTV term and be em- bedded into an HSI processing model to ameliorate its performance. The superiority of the proposed methods is substantiated by extensive experiments on two typical related tasks: HSI denoising and compressed sensing, as compared with state-of-the-arts designed for both tasks.

cs.CV↗

arXiv2018

Correlated structure of nuclear symmetry energy from covariant nucleon self-energy

Based on the Hugenholtz-Van Hove theorem, the symmetry energy $J$ and its density slope parameter $L$ are decomposed in terms of the nucleon self-energies within the covariant density functional (CDF) theory. It is found that two structural connections between the different ingredients of $J$ and $L$ construct the fundamental correlation between $L$ and $J$ in the relativistic covariant framework, while the additional contribution from the isovector scalar channel of nucleon-nucleon interaction and those from the second-order symmetry self-energies lead to a deviation, especially the latter limits severely its correlation coefficient and confidence level. In addition, the relationship between the Landau mass $M_L^*$ and the Dirac mass $M_D^*$ is approximated to a reliable linear correlation, which is demonstrate to be sensitive to the momentum dependence of the nucleon self-energies.

nucl-th↗

arXiv2018

Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement

Recently, deep learning(DL) methods have been proposed for the low-dose computed tomography(LdCT) enhancement, and obtain good trade-off between computational efficiency and image quality. Most of them need large number of pre-collected ground-truth/high-dose sinograms with less noise, and train the network in a supervised end-to-end manner. This may bring major limitations on these methods because the number of such low-dose/high-dose training sinogram pairs would affect the network's capability and sometimes the ground-truth sinograms are hard to be obtained in large scale. Since large number of low-dose ones are relatively easy to obtain, it should be critical to make these sources play roles in network training in an unsupervised learning manner. To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training. The proposed method effectively considers the structure characteristics and noise distribution in the measured LdCT sinogram, and then learns the proper gradient of the LdCT sinogram in a pure unsupervised manner. Similar to the labeled ground-truth, the gradient information in an unlabeled LdCT sinogram can be used for sufficient network training. The experiments on the patient data show effectiveness of the proposed method.

cs.CV↗

arXiv2018

Casimir repulsive-attractive transition between liquid-separated dielectric metamaterial and metal

We study the repulsive-attractive transition, regarded as stable equilibrium, between gold and dielectric metamaterial based on Mie resonance immersed in various fluids due to the interplay of gravity, buoyancy and Casimir force among different geometries consisting of parallel plates and spheres levitated over substrates. A wider range of separation distance of stable equilibrium is obtained with Mie metamaterial than natural materials. We investigate the relationship between separation distance of stable equilibrium and constructive parameters of Mie metamaterial and geometric parameters of the system, and provide simple rules to tune the equilibrium position by modifying constructive parameters of Mie metamaterial. Particularly, the effect of permeability of Mie metamaterial on equilibrium separation is also considered. Our work is promising for potential applications in frictionless suspension in micro/nanofabrication technologies.

physics.app-ph↗

arXiv2017

Extreme case of Faraday effect: magnetic splitting of ultrashort laser pulses in plasmas

The Faraday effect, caused by a magnetic-field-induced change in the optical properties, takes place in a vast variety of systems from a single atomic layer of graphenes to huge galaxies. Currently, it plays a pivot role in many applications such as the manipulation of light and the probing of magnetic fields and material's properties. Basically, this effect causes a polarization rotation of light during its propagation along the magnetic field in a medium. Here, we report an extreme case of the Faraday effect where a linearly polarized ultrashort laser pulse splits in time into two circularly polarized pulses of opposite handedness during its propagation in a highly magnetized plasma. This offers a new degree of freedom for manipulating ultrashort and ultrahigh power laser pulses. Together with technologies of ultra-strong magnetic fields, it may pave the way for novel optical devices, such as magnetized plasma polarizers. In addition, it may offer a powerful means to measure strong magnetic fields in laser-produced plasmas.

physics.plasm-ph↗

arXiv2017

Hyperspectral Image Restoration via Total Variation Regularized Low-rank Tensor Decomposition

Hyperspectral images (HSIs) are often corrupted by a mixture of several types of noise during the acquisition process, e.g., Gaussian noise, impulse noise, dead lines, stripes, and many others. Such complex noise could degrade the quality of the acquired HSIs, limiting the precision of the subsequent processing. In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part respectively. Specifically, for the clean HSI part, we use tensor Tucker decomposition to describe the global correlation among all bands, and an anisotropic spatial-spectral total variation (SSTV) regularization to characterize the piecewise smooth structure in both spatial and spectral domains. For the mixed noise part, we adopt the $\ell_1$ norm regularization to detect the sparse noise, including stripes, impulse noise, and dead pixels. Despite that TV regulariztion has the ability of removing Gaussian noise, the Frobenius norm term is further used to model heavy Gaussian noise for some real-world scenarios. Then, we develop an efficient algorithm for solving the resulting optimization problem by using the augmented Lagrange multiplier (ALM) method. Finally, extensive experiments on simulated and real-world noise HSIs are carried out to demonstrate the superiority of the proposed method over the existing state-of-the-art ones.

cs.CV↗

arXiv2017

SPLBoost: An Improved Robust Boosting Algorithm Based on Self-paced Learning

It is known that Boosting can be interpreted as a gradient descent technique to minimize an underlying loss function. Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers. Therefore, several Boosting algorithms, e.g., LogitBoost and SavageBoost, have been proposed to improve the robustness of AdaBoost by replacing the exponential loss with some designed robust loss functions. In this work, we present a new way to robustify AdaBoost, i.e., incorporating the robust learning idea of Self-paced Learning (SPL) into Boosting framework. Specifically, we design a new robust Boosting algorithm based on SPL regime, i.e., SPLBoost, which can be easily implemented by slightly modifying off-the-shelf Boosting packages. Extensive experiments and a theoretical characterization are also carried out to illustrate the merits of the proposed SPLBoost.

cs.CV↗

arXiv2017

Robust Tracking Guidance for Zero Propellant Maneuver

The Zero Propellant Maneuver (ZPM) maneuvers the space station by large angle, utilizing the Control Momentum Gyroscopes (CMGs) only. A robust tracking guidance strategy is proposed to enhance its performance. It is distinguished from the traditional trajectory tracking guidance in that the reference trajectory is adjusted on-line, under the inspiration of eliminating the discrepancy on the total angular momentum of the space station system. The Lyapunov controller is developed to adjust the attitude trajectory and further redesigned for a better performance based on an interesting physical phenomenon, which is taken advantage of by coupling the components of state vector. The adjusted trajectory is then tracked to reach the target states of maneuver. Simulations results show that the disturbance effects arising from initial state errors, parameter uncertainty and modeling errors are attenuated or even eliminated, which verifies the robustness of the guidance strategy.

eess.SY↗

arXiv2017

A General Model for Robust Tensor Factorization with Unknown Noise

Because of the limitations of matrix factorization, such as losing spatial structure information, the concept of low-rank tensor factorization (LRTF) has been applied for the recovery of a low dimensional subspace from high dimensional visual data. The low-rank tensor recovery is generally achieved by minimizing the loss function between the observed data and the factorization representation. The loss function is designed in various forms under different noise distribution assumptions, like $L_1$ norm for Laplacian distribution and $L_2$ norm for Gaussian distribution. However, they often fail to tackle the real data which are corrupted by the noise with unknown distribution. In this paper, we propose a generalized weighted low-rank tensor factorization method (GWLRTF) integrated with the idea of noise modelling. This procedure treats the target data as high-order tensor directly and models the noise by a Mixture of Gaussians, which is called MoG GWLRTF. The parameters in the model are estimated under the EM framework and through a new developed algorithm of weighted low-rank tensor factorization. We provide two versions of the algorithm with different tensor factorization operations, i.e., CP factorization and Tucker factorization. Extensive experiments indicate the respective advantages of this two versions in different applications and also demonstrate the effectiveness of MoG GWLRTF compared with other competing methods.

cs.CV↗