Search

Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require complex computation and thus computational pricy, especially for stitching large raw images. In this study, inspired by the multiscale feature of fluid turbulence, we developed a fast feature point detection algorithm named local-peak scale-invariant feature transform (LP-SIFT), based on the multiscale local peaks and scale-invariant feature transform method. By combining LP-SIFT and RANSAC in image stitching, the stitching speed can be improved by orders, compared with the original SIFT method. Nine large images (over 2600*1600 pixels), arranged randomly without prior knowledge, can be stitched within 158.94 s. The algorithm is highly practical for applications requiring a wide field of view in diverse application scenes, e.g., terrain mapping, biological analysis, and even criminal investigation.

Traditionally, results given by the direct numerical simulation (DNS) of Navier-Stokes equations are widely regarded as reliable benchmark solutions of turbulence, as long as grid spacing is fine enough (i.e. less than the minimum Kolmogorov scale) and time-step is small enough, say, satisfying the Courant-Friedrichs-Lewy condition. Is this really true? In this paper a two-dimensional sustained turbulent Kolmogorov flow is investigated numerically by the two numerical methods with detailed comparisons: one is the traditional `direct numerical simulation' (DNS), the other is the `clean numerical simulation' (CNS). The results given by DNS are a kind of mixture of the false numerical noise and the true physical solution, which however are mostly at the same order of magnitude due to the butterfly-effect of chaos. On the contrary, the false numerical noise of the results given by CNS is much smaller than the true physical solution of turbulence in a long enough interval of time so that a CNS result is very close to the true physical solution and thus can be used as a benchmark solution. It is found that numerical noise as a kind of artificial tiny disturbances can lead to huge deviations at large scale on the two-dimensional Kolmogorov turbulence, not only quantitatively (even in statistics) but also qualitatively (such as symmetry of flow). Thus, fine enough spatial grid spacing with small enough time-step alone cannot guarantee the validity of the DNS: it is only a necessary condition but not sufficient. This finding might challenge some assumptions in investigation of turbulence. So, DNS results of a few sustained turbulent flows might have huge deviations on both of small and large scales from the true solution of Navier-Stokes equations even in statistics. Hopefully, CNS as a new tool to investigate turbulent flows more accurately than DNS could bring us some new discoveries., Comment: 27 pages, 18 figures

This paper addresses the blind recovery of the parity check matrix of an (n,k) linear block code over noisy channels by proposing a fast recovery scheme consisting of 3 parts. Firstly, this scheme performs initial error position detection among the received codewords and selects the desirable codewords. Then, this scheme conducts Gaussian elimination (GE) on a k-by-k full-rank matrix and uses a threshold and the reliability associated to verify the recovered dual words, aiming to improve the reliability of recovery. Finally, it performs decoding on the received codewords with partially recovered dual words. These three parts can be combined into different schemes for different noise level scenarios. The GEV that combines Gaussian elimination and verification has a significantly lower recovery failure probability and a much lower computational complexity than an existing Canteaut-Chabaud-based algorithm, which relies on GE on n-by-n full-rank matrices. The decoding-aided recovery (DAR) and error-detection-&-codeword-selection-&-decoding-aided recovery (EDCSDAR) schemes can improve the code recovery performance over GEV for high noise level scenarios, and their computational complexities remain much lower than the Canteaut-Chabaud-based algorithm., Comment: 9 pages, 4 figures

For EEG-based drowsiness recognition, it is desirable to use subject-independent recognition since conducting calibration on each subject is time-consuming. In this paper, we propose a novel Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) model for subject-independent drowsiness recognition from single-channel EEG signals. Different from existing deep learning models that are mostly treated as black-box classifiers, the proposed model can explain its decisions for each input sample by revealing which parts of the sample contain important features identified by the model for classification. This is achieved by a visualization technique by taking advantage of the hidden states output by the LSTM layer. Results show that the model achieves an average accuracy of 72.97% on 11 subjects for leave-one-out subject-independent drowsiness recognition on a public dataset, which is higher than the conventional baseline methods of 55.42%-69.27%, and state-of-the-art deep learning methods. Visualization results show that the model has discovered meaningful patterns of EEG signals related to different mental states across different subjects.

Recent advancements in computational resources and Deep Learning methodologies has significantly benefited development of intelligent vision-based surveillance applications. Gait recognition in the presence of occlusion is one of the challenging research topics in this area, and the solutions proposed by researchers to date lack in robustness and also dependent of several unrealistic constraints, which limits their practical applicability. We improve the state-of-the-art by developing novel deep learning-based algorithms to identify the occluded frames in an input sequence and next reconstruct these occluded frames by exploiting the spatio-temporal information present in the gait sequence. The multi-stage pipeline adopted in this work consists of key pose mapping, occlusion detection and reconstruction, and finally gait recognition. While the key pose mapping and occlusion detection phases are done %using Constrained KMeans Clustering and via a graph sorting algorithm, reconstruction of occluded frames is done by fusing the key pose-specific information derived in the previous step along with the spatio-temporal information contained in a gait sequence using a Bi-Directional Long Short Time Memory. This occlusion reconstruction model has been trained using synthetically occluded CASIA-B and OU-ISIR data, and the trained model is termed as Bidirectional Gait Reconstruction Network BGait-R-Net. Our LSTM-based model reconstructs occlusion and generates frames that are temporally consistent with the periodic pattern of a gait cycle, while simultaneously preserving the body structure.

We study the three-dimensional turbulent Kolmogorov flow, i.e. the Navier-Stokes equations forced by a low-single-wave-number sinusoidal force in a periodic domain, by means of direct numerical simulations. This classical model system is a realization of anisotropic and non-homogeneous hydrodynamic turbulence. Boussinesq's eddy viscosity linear relation is checked and found to be approximately valid over half of the system volume. A more general nonlinear quadratic Reynolds stress development is proposed and its parameters estimated at varying the Taylor scale-based Reynolds number in the flow up to the value 200. The case of a forcing with a different shape, here chosen Gaussian, is considered and the differences with the sinusoidal forcing are emphasized., Comment: 11 pages

The statistical properties of species undergoing chemical reactions in a turbulent environment are studied. We focus on the case of reversible multi-component reactions of second and higher orders, in a condition close to chemical equilibrium sustained by random large-scale reactant sources, while the turbulent flow is highly developed. In such a state a competition exists between the chemical reaction that tends to dump reactant concentration fluctuations and enhance their correlation intensity and the turbulent mixing that on the contrary increases fluctuations and remove relative correlations. We show that a unique control parameter, the Damkh\"{o}ler number ($Da_\theta$) that can be constructed from the scalar Taylor micro-scale, the reactant diffusivity and the reaction rate characterises the functional dependence of fluctuations and correlations in a variety of conditions, i.e., at changing the reaction order, the Reynolds and the Schmidt numbers. The larger is such a Damkh\"{o}ler number the more depleted are the scalar fluctuations as compared to the fluctuations of a passive scalar field in the same conditions, and vice-versa the more intense are the correlations. A saturation in this behaviour is observed beyond $Da_\theta \simeq \mathcal{O}(10)$. We provide an analytical prediction for this phenomenon which is in excellent agreement with direct numerical simulation results., Comment: 17 pages , 9 figures

While deep learning technologies are now capable of generating realistic images confusing humans, the research efforts are turning to the synthesis of images for more concrete and application-specific purposes. Facial image generation based on vocal characteristics from speech is one of such important yet challenging tasks. It is the key enabler to influential use cases of image generation, especially for business in public security and entertainment. Existing solutions to the problem of speech2face renders limited image quality and fails to preserve facial similarity due to the lack of quality dataset for training and appropriate integration of vocal features. In this paper, we investigate these key technical challenges and propose Speech Fusion to Face, or SF2F in short, attempting to address the issue of facial image quality and the poor connection between vocal feature domain and modern image generation models. By adopting new strategies on data model and training, we demonstrate dramatic performance boost over state-of-the-art solution, by doubling the recall of individual identity, and lifting the quality score from 15 to 19 based on the mutual information score with VGGFace classifier.

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field., Comment: Published in Sensors Journal (https://www.mdpi.com/1424-8220/20/18/5097)

Gait of a person refers to his/her walking pattern, and according to medical studies gait of every individual is unique. Over the past decade, several computer vision-based gait recognition approaches have been proposed in which walking information corresponding to a complete gait cycle has been used to construct gait features for person identification. These methods compute gait features with the inherent assumption that a complete gait cycle is always available. However, in most public places occlusion is an inevitable occurrence, and due to this, only a fraction of a gait cycle gets captured by the monitoring camera. Unavailability of complete gait cycle information drastically affects the accuracy of the extracted features, and till date, only a few occlusion handling strategies to gait recognition have been proposed. But none of these performs reliably and robustly in the presence of a single cycle with incomplete information, and because of this practical application of gait recognition is quite limited. In this work, we develop deep learning-based algorithm to accurately identify the affected frames as well as predict the missing frames to reconstruct a complete gait cycle. While occlusion detection has been carried out by employing a VGG-16 model, the model for frame reconstruction is based on Long-Short Term Memory network that has been trained to optimize a multi-objective function based on dice coefficient and cross-entropy loss. The effectiveness of the proposed occlusion reconstruction algorithm is evaluated by computing the accuracy of the popular Gait Energy Feature on the reconstructed sequence. Experimental evaluation on public data sets and comparative analysis with other occlusion handling methods verify the effectiveness of our approach., Comment: 10 pages

The geometrical structure is among the most fundamental ingredients in understanding complex systems. Is there any systematic approach in defining structures quantitatively, rather than illustratively? If yes, what are the basic principles to follow? By introducing the concept of extremal points at different scale levels, a multi-level dissipation element approach has been developed to define structures at different scale levels, in accordance with the concept of structure hierarchy. Each dissipation element can be characterized by the length scale and the scalar variance inside. Using the two-dimensional fractal Brownian motion as a benchmark case, the conditional mean of the scalar difference with respect to the length scale shows clearly a power law and the scaling exponent is in agreement with the Hurst number. For the 3D turbulence velocity component, the 1/3 scaling law can be represented. These results indicate the important linkage between the turbulence physics and ow structure, if well posed and defined. In principle, the multi-level dissipation element idea is generally applicable in analyzing other multiscale complex systems as well., Comment: This paper will be revised and new results will be added

Image de-fencing is one of the important aspects of recreational photography in which the objective is to remove the fence texture present in an image and generate an aesthetically pleasing version of the same image without the fence texture. In this paper, we aim to develop an automated and effective technique for fence removal and image reconstruction using conditional Generative Adversarial Networks (cGANs). These networks have been successfully applied in several domains of Computer Vision focusing on image generation and rendering. Our initial approach is based on a two-stage architecture involving two cGANs that generate the fence mask and the inpainted image, respectively. Training of these networks is carried out independently and, during evaluation, the input image is passed through the two generators in succession to obtain the de-fenced image. The results obtained from this approach are satisfactory, but the response time is long since the image has to pass through two sets of convolution layers. To reduce the response time, we propose a second approach involving only a single cGAN architecture that is trained using the ground-truth of fenced de-fenced image pairs along with the edge map of the fenced image produced by the Canny Filter. Incorporation of the edge map helps the network to precisely detect the edges present in the input image, and also imparts it an ability to carry out high quality de-fencing in an efficient manner, even in the presence of a fewer number of layers as compared to the two-stage network. Qualitative and quantitative experimental results reported in the manuscript reveal that the de-fenced images generated by the single-stage de-fencing network have similar visual quality to those produced by the two-stage network. Comparative performance analysis also emphasizes the effectiveness of our approach over state-of-the-art image de-fencing techniques., Comment: 10 pages, 5 figures

Context. Multiple automated techniques have been proposed and developed for mobile application GUI testing aiming to improve effectiveness, efficiency, and practicality. The effectiveness, efficiency, and practicality are 3 fundamental characteristics which testing techniques are built upon, and need to be continuously improved to deliver useful solutions for researchers and practitioners, and community as a whole. Objective. In this systematic review, we attempt to provide a broad picture of existing mobile testing tools by collating and analysing their conceptual, and also performance characteristics including an estimation of effectiveness, efficiency, and practicality. Method. To achieve our objective, we specify 3 primary, and 14 secondary review questions, and conducted an analysis of 25 primary studies. We first individually analyse each primary study, and next analyse the primary studies as a whole. We developed a review protocol which defines all the details of our systematic review. Results. From effectiveness, we conclude that testing techniques which implement model-checking, symbolic execution, constraint solving, and search-based test generation approach tend to be more effective than those implementing random test generation. From efficiency, we conclude that testing techniques which implement code search-based testing approaches tend to be more efficient than those implementing GUI model-based. From practicality, we conclude that the more effective a testing technique is, the less efficient it will be. Conclusion. For effectiveness, we observe that the existing automated testing techniques are not effective enough, and currently they achieve nearly half of the desired level of effectiveness. For efficiency, we observe that current automated testing techniques are not efficient enough., Comment: GUI testing, Functional testing, Model-based, Mobile, Systematic literature review

In this paper, we analyze the sea surface temperature obtained from the global drifter program. The experimental Fourier power spectrum shows a two-decade power-law behavior as $E_{\theta}(f)\propto f^{-7/3}$ in the frequency domain. Dimensional argument suggests a two-dimensional-like Lagrangian forward cascade, in which the enstrophy dissipation $\epsilon_{\Omega}$ is involved. Using the Hilbert-Huang transform and multi-level segment analysis, the measured high-order statistics and the corresponding singularity spectrum confirm the existence of the intermittency with a measured intermittency parameter $\mu_{\theta}\simeq0.10$, which is much weaker than the prediction by the conventional structure function method., Comment: 19 pages with 9 figures

The self-similarity of a passive scalar in homogeneous isotropic decaying turbulence is investigated by the method of line segments (M. Gauding et al., Physics of Fluids 27.9 (2015): 095102). The analysis is based on a highly resolved direct numerical simulation of decaying turbulence. The method of line segments is used to perform a decomposition of the scalar field into smaller sub-units based on the extremal points of the scalar along a straight line. These sub-units (the so-called line segments) are parameterized by their length $\ell$ and the difference $\Delta\phi$ of the scalar field between the ending points. Line segments can be understood as thin local convective-diffusive structures in which diffusive processes are enhanced by compressive strain. From DNS, it is shown that the marginal distribution function of the length~$\ell$ assumes complete self-similarity when re-scaled by the mean length $\ell_m$. The joint statistics of $\Delta\phi$ and $\ell$, from which the local gradient $g=\Delta\phi/\ell$ can be defined, play an important role in understanding the turbulence mixing and flow structure. Large values of $g$ occur at a small but finite length scale. Statistics of $g$ are characterized by rare but strong deviations that exceed the standard deviation by more than one order of magnitude. It is shown that these events break complete self-similarity of line segments, which confirms the standard paradigm of turbulence that intense events (which are known as internal intermittency) are not self-similar.

In recent years several local extrema based methodologies have been proposed to investigate either the nonlinear or the nonstationary time series for scaling analysis. In the present work we study systematically the distribution of the local extrema for both synthesized scaling processes and turbulent velocity data from experiments. The results show that for the fractional Brownian motion (fBm) without intermittency correction the measured extremal point density (EPD) agrees well with a theoretical prediction. For a multifractal random walk (MRW) with the lognormal statistics, the measured EPD is independent with the intermittency parameter $\mu$, suggesting that the intermittency correction does not change the distribution of extremal points, but change the amplitude. By introducing a coarse-grained operator, the power-law behavior of these scaling processes is then revealed via the measured EPD for different scales. For fBm the scaling exponent $\xi(H)$ is found to be $\xi(H)=H$, where $H$ is Hurst number, while for MRW $\xi(H)$ shows a linear relation with the intermittency parameter $\mu$. Such EPD approach is further applied to the turbulent velocity data obtained from a wind tunnel flow experiment with the Taylor scale $\lambda$ based Reynolds number $Re_{\lambda}= 720$, and a turbulent boundary layer with the momentum thickness $\theta$ based Reynolds number $Re_{\theta}= 810$. A scaling exponent $\xi\simeq 0.37$ is retrieved for the former case. For the latter one, the measured EPD shows clearly four regimes, which agree well with the four regimes of the turbulent boundary layer structures., Comment: 26 pages with 19 figures

The active interaction between the bacteria and fluid generates turbulent structures even at zero Reynolds number. Velocity of such a flow obtained experimentally has been quantitatively investigated based on streamline segment analysis. There is a clear transition at about $16$ times of the organism body length separating two different scale regimes, which may be attributed to the different influence of the viscous effect. Surprisingly the scaling extracted from the streamline segment indicates the existence of scale similarity even at the zero Reynolds number limit. Moreover the multifractal feature can be quantitatively described via a lognormal formula with the Hurst number $H=0.76$ and the intermittency parameter $\mu=0.20$, which is coincidentally in agreement with the three-dimensional hydrodynamic turbulence result. The direction of cascade is measured via the filter-space technique. An inverse energy cascade is confirmed. For the enstrophy, a forward cascade is observed when $r/R\le 3$, and an inverse one is observed when $r/R>3$. Additionally, the lognormal statistics is verified for the coarse-grained energy dissipation and enstrophy, which supports the lognormal formula to fit the measured scaling exponent., Comment: 17 pages, 8 figures

Building behavior profiles of Android applications (apps) with holistic, rich and multi-view information (e.g., incorporating several semantic views of an app such as API sequences, system calls, etc.) would help catering downstream analytics tasks such as app categorization, recommendation and malware analysis significantly better. Towards this goal, we design a semi-supervised Representation Learning (RL) framework named apk2vec to automatically generate a compact representation (aka profile/embedding) for a given app. More specifically, apk2vec has the three following unique characteristics which make it an excellent choice for largescale app profiling: (1) it encompasses information from multiple semantic views such as API sequences, permissions, etc., (2) being a semi-supervised embedding technique, it can make use of labels associated with apps (e.g., malware family or app category labels) to build high quality app profiles, and (3) it combines RL and feature hashing which allows it to efficiently build profiles of apps that stream over time (i.e., online learning). The resulting semi-supervised multi-view hash embeddings of apps could then be used for a wide variety of downstream tasks such as the ones mentioned above. Our extensive evaluations with more than 42,000 apps demonstrate that apk2vec's app profiles could significantly outperform state-of-the-art techniques in four app analytics tasks namely, malware detection, familial clustering, app clone detection and app recommendation., Comment: International Conference on Data Mining, 2018

The temporal statistics of incompressible fluid velocity and passive scalar fields in developed turbulent conditions is investigated by means of direct numerical simulations along the trajectories of self-propelled point-like probes drifting in a flow. Such probes are characterised by a propulsion velocity which is fixed in intensity and direction; however, like vessels in a flow they are continuously deviated by their intended course as the result of local sweeping of the fluid flow. The recorded time-series by these moving probes represent the simplest realisation of transect measurements in a fluid flow environment. We investigate the non trivial combination of Lagrangian and Eulerian statistical properties displayed by the transect time-series. We show that, as a result of the homogeneity and isotropy of the flow, the single-point acceleration statistics of the probes follows a predictable trend at varying the propulsion speed, a feature that is also present in the scalar time-derivative fluctuations. Further, by focusing on two-time statistics we characterize how the Lagrangian-to-Eulerian transition occurs at increasing the propulsion velocity. The analysis of intermittency of temporal increments highlights in a striking way the opposite trends displayed by the fluid velocity and passive scalars., Comment: 12 pages, 7 figures + supplementary

It is of broad interest to understand how the evolution of non-equilibrium systems can be triggered and the role played by external perturbations. A famous example is the origin of randomness in the laminar-turbulence transition, which is raised in the pipe flow experiment by Reynolds as a century old unresolved problem. Although there exist different hypotheses, it is widely believed that the randomness is "intrinsic", which, however, remains as an open question to be verified. Simulating the modeled Rayleigh-Benard convection system by means of the so-called clean numerical simulation (CNS) with negligible numerical noises that are smaller even than thermal fluctuation, we verify that turbulence can be self-excited from the inherent thermal fluctuation, without any external disturbances, i.e. out of nothing. This reveals a relationship between microscopic physical uncertainty and macroscopic randomness. It is found that in physics the system nonlinearity functions as a channel for randomness information, and energy as well, to transport microscopic uncertainty toward large scales. Such scenario can generally be helpful to understand the various relevant phenomena. In methodology, compared with direct numerical simulation (DNS), CNS opens a new direction to investigate turbulent flows with largely improved accuracy and reliability., Comment: http://engine.scichina.com/doi/10.1007/s11433-016-0401-5