GREYC

In this paper, we focus on techniques for vector-valued image regularization, based on variational methods and PDEs. Starting from the study of PDE-based formalisms previously proposed in the literature for the regularization of scalar and vector-valued data, we propose a unifying expression that gathers the majority of these previous frameworks into a single generic anisotropic diffusion equation. On one hand, the resulting expression provides a simple interpretation of the regularization process in terms of local filtering with spatially adaptive Gaussian kernels. On the other hand, it naturally disassembles any regularization scheme into the smoothing process itself and the underlying geometry that drives the smoothing. Thus, we can easily specialize our generic expression into different regularization PDEs that fulfill desired smoothing behaviors, depending on the considered application: image restoration, inpainting, magnification, flow visualization, etc. Specific numerical schemes are also proposed, allowing us to implement our regularization framework with accuracy by taking the local filtering properties of the proposed equations into account. Finally, we illustrate the wide range of applications handled by our selected anisotropic diffusion equations with application results on color images.

Nowadays, there is a trend to design complex, yet secure systems. In this context, the Trusted Execution Environment (TEE) was designed to enrich the previously defined trusted platforms. TEE is commonly known as an isolated processing environment in which applications can be securely executed irrespective of the rest of the system. However, TEE still lacks a precise definition as well as representative building blocks that systematize its design. Existing definitions of TEE are largely inconsistent and unspecific, which leads to confusion in the use of the term and its differentiation from related concepts, such as secure execution environment (SEE). In this paper, we propose a precise definition of TEE and analyze its core properties. Furthermore, we discuss important concepts related to TEE, such as trust and formal verification. We give a short survey on the existing academic and industrial ARM TrustZone-based TEE, and compare them using our proposed definition. Finally, we discuss some known attacks on deployed TEE as well as its wide use to guarantee security in diverse applications.

We present a family of scale-invariant local shape features formed by chains of k connected, roughly straight contour segments (kAS), and their use for object class detection. kAS are able to cleanly encode pure fragments of an object boundary, without including nearby clutter. Moreover, they offer an attractive compromise between information content and repeatability, and encompass a wide variety of local shape structures. We also define a translation and scale invariant descriptor encoding the geometric configuration of the segments within a kAS, making kAS easy to reuse in other frameworks, for example as a replacement or addition to interest points. Software for detecting and describing kAS is released on lear.inrialpes.fr/software. We demonstrate the high performance of kAS within a simple but powerful sliding-window object detection scheme. Through extensive evaluations, involving eight diverse object classes and more than 1400 images, we 1) study the evolution of performance as the degree of feature complexity k varies and determine the best degree; 2) show that kAS substantially outperform interest points for detecting shape-based classes; 3) compare our object detector to the recent, state-of-the-art system by Dalal and Triggs [4].

This paper describes the undecimated wavelet transform and its reconstruction. In the first part, we show the relation between two well known undecimated wavelet transforms, the standard undecimated wavelet transform and the isotropic undecimated wavelet transform. Then we present new filter banks specially designed for undecimated wavelet decompositions which have some useful properties such as being robust to ringing artifacts which appear generally in wavelet-based denoising methods. A range of examples illustrates the results

We introduce a nonlocal discrete regularization framework on weighted graphs of the arbitrary topologies for image and manifold processing. The approach considers the problem as a variational one, which consists of minimizing a weighted sum of two energy terms: a regularization one that uses a discrete weighted p-Dirichlet energy and an approximation one. This is the discrete analogue of recent continuous Euclidean nonlocal regularization functionals. The proposed formulation leads to a family of simple and fast nonlinear processing methods based on the weighted p-Laplace operator, parameterized by the degree p of regularity, the graph structure and the graph weight function. These discrete processing methods provide a graph-based version of recently proposed semi-local or nonlocal processing methods used in image and mesh processing, such as the bilateral filter, the TV digital filter or the nonlocal means filter. It works with equal ease on regular 2-D and 3-D images, manifolds or any data. We illustrate the abilities of the approach by applying it to various types of images, meshes, manifolds, and data represented as graphs.

This paper introduces a generalized forward-backward splitting algorithm for finding a zero of a sum of maximal monotone operators $B + \sum_{i=1}^n A_i$, where $B$ is cocoercive. It involves the computation of $B$ in an explicit (forward) step and the parallel computation of the resolvents of the $A_i$'s in a subsequent implicit (backward) step. We prove the algorithm's convergence in infinite dimension and its robustness to summable errors on the computed operators in the explicit and implicit steps. In particular, this allows efficient minimization of the sum of convex functions $f + \sum_{i=1}^n g_i$, where $f$ has a Lipschitz-continuous gradient and each $g_i$ is simple in the sense that its proximity operator is easy to compute. The resulting method makes use of the regularity of $f$ in the forward step, and the proximity operators of the $g_i$'s are applied in parallel in the backward step. While the forward-backward algorithm cannot deal with more than $n = 1$ nonsmooth function, we generalize it to the case of arbitrary $n$. Examples on inverse problems in imaging demonstrate the advantage of the proposed methods in comparison to other splitting algorithms.

In order to denoise Poisson count data, we introduce a variance stabilizing transform (VST) applied on a filtered discrete Poisson process, yielding a near Gaussian process with asymptotic constant variance. This new transform, which can be deemed as an extension of the Anscombe transform to filtered data, is simple, fast, and efficient in (very) low-count situations. We combine this VST with the filter banks of wavelets, ridgelets and curvelets, leading to multiscale VSTs (MS-VSTs) and nonlinear decomposition schemes. By doing so, the noise-contaminated coefficients of these MS-VST-modified transforms are asymptotically normally distributed with known variances. A classical hypothesis-testing framework is adopted to detect the significant coefficients, and a sparsity-driven iterative scheme reconstructs properly the final estimate. A range of examples show the power of this MS-VST approach for recovering important structures of various morphologies in (very) low-count images. These results also demonstrate that the MS-VST approach is competitive relative to many existing denoising methods.

Representing the image to be inpainted in an appropriate sparse representation dictionary, and combining elements from Bayesian statistics and modern harmonic analysis, we introduce an expectation maximization (EM) algorithm for image inpainting and interpolation. From a statistical point of view, the inpainting/interpolation can be viewed as an estimation problem with missing data. Toward this goal, we propose the idea of using the EM mechanism in a Bayesian framework, where a sparsity promoting prior penalty is imposed on the reconstructed coefficients. The EM framework gives a principled way to establish formally the idea that missing samples can be recovered/ interpolated based on sparse representations. We first introduce an easy and efficient sparserepresentation-based iterative algorithm for image inpainting. Additionally, we derive its theoretical convergence properties. Compared to its competitors, this algorithm allows a high degree of flexibility to recover different structural components in the image (piecewise smooth, curvilinear, texture, etc.). We also suggest some guidelines to automatically tune the regularization parameter.

This book presents the state of the art in sparse and multiscale image and signal processing, covering linear multiscale transforms, such as wavelet, ridgelet, or curvelet transforms, and non-linear multiscale transforms based on the median and mathematical morphology operators. Recent concepts of sparsity and morphological diversity are described and exploited for various problems such as denoising, inverse problem regularization, sparse signal decomposition, blind source separation, and compressed sensing. This book weds theory and practice in examining applications in areas such as astronomy, biology, physics, digital media, and forensics. A final chapter explores a paradigm shift in signal processing, showing that previous limits to information sampling and extraction can be overcome in very significant ways. Matlab and IDL code accompany these methods and applications to reproduce the experiments and illustrate the reasoning and methodology of the research are available for download at the associated web site

Social phobia is one of the most frequent mental disorders and is accessible to two forms of scientifically validated treatments: anti-depressant drugs and cognitive behavior therapies (CBT). In this last case, graded exposure to feared social situations is one of the fundamental therapeutic ingredients. Virtual reality technologies are an interesting alternative to the standard exposure in social phobia, especially since studies have shown its usefulness for the fear of public speaking. This paper reports a preliminary study in which a virtual reality therapy (VRT), based on exposure to virtual environments, was used to treat social phobia. The sample consisted of 36 participants diagnosed with social phobia assigned to either VRT or a group-CBT (control condition). The virtual environments used in the treatment recreate four situations dealing with social anxiety: performance, intimacy, scrutiny, and assertiveness. With the help of the therapist, the patient learns adapted cognitions and behaviors in order to reduce anxiety in the corresponding real situations. Both treatments lasted 12 weeks, and sessions were delivered according to a treatment manual. Results showed statistically and clinically significant improvement in both conditions. The effect-sizes comparing the efficacy of VRT to the control traditional group-CBT revealed that the differences between the two treatments are trivial.

In a recent paper, a method called morphological component analysis (MCA) has been proposed to separate the texture from the natural part in images. MCA relies on an iterative thresholding algorithm, using a threshold which decreases linearly towards zero along the iterations. This paper shows how the MCA convergence can be drastically improved using the mutual incoherence of the dictionaries associated to the different components. This modified MCA algorithm is then compared to basis pursuit, and experiments show that MCA and BP solutions are similar in terms of sparsity, as measured by the l1 norm, but MCA is much faster and gives us the possibility of handling large scale data sets.

Locating moving objects in a video sequence is the first step of many computer vision applications. Among the various motion-detection techniques, background subtraction methods are commonly implemented, especially for applications relying on a fixed camera. Since the basic inter-frame difference with global threshold is often a too simplistic method, more elaborate (and often probabilistic) methods have been proposed. These methods often aim at making the detection process more robust to noise, background motion and camera jitter. In this paper, we present commonly-implemented background subtraction algorithms and we evaluate them quantitatively. In order to gauge performances of each method, tests are performed on a wide range of real, synthetic and semi-synthetic video sequences representing different challenges.

Adaptive control provides techniques for adjusting control parameters in real time to maintain system performance despite unknown or changing process parameters. These methods use real data to tune controllers and adjust plant models or controller parameters. The field has progressed significantly since the 1970s, helped by digital computers. Early applications offered essential feedback, and theoretical advances solved many basic problems. This book comprehensively treats adaptive control, guiding readers from basic problems to analytical solutions with practical applications. Presenting a unified view is challenging due to various design steps and applications. However, a coherent presentation of basic techniques is now possible. The book uses a discrete-time approach to reflect the role of digital computers and shares practical experiences and understanding of different control designs. Mathematical aspects of synthesizing and analyzing algorithms are emphasized, though they alone may not solve practical problems. The book includes applications of control techniques but stresses that a solid mathematical understanding is crucial for creatively applying them to new challenges. Mathematical synthesis and analysis are highlighted, but they must be supplemented with practical problem-solving and algorithm modifications for specific applications.

AIM: Evaluation of the diagnostic accuracy of stress perfusion cardiovascular magnetic resonance for the diagnosis of significant obstructive coronary artery disease (CAD) through meta-analysis of the available data. METHODOLOGY: Original articles in any language published before July 2009 were selected from available databases (MEDLINE, Cochrane Library and BioMedCentral) using the combined search terms of magnetic resonance, perfusion, and coronary angiography; with the exploded term coronary artery disease. Statistical analysis was only performed on studies that: (1) used a [greater than or equal to] 1.5 Tesla MR scanner; (2) employed invasive coronary angiography as the reference standard for diagnosing significant obstructive CAD, defined as a [greater than or equal to] 50% diameter stenosis; and (3) provided sufficient data to permit analysis. RESULTS: From the 263 citations identified, 55 relevant original articles were selected. Only 35 fulfilled all of the inclusion criteria, and of these 26 presented data on patient-based analysis. The overall patient-based analysis demonstrated a sensitivity of 89% (95% CI: 88-91%), and a specificity of 80% (95% CI: 78-83%). Adenosine stress perfusion CMR had better sensitivity than with dipyridamole (90% (88-92%) versus 86% (80-90%), P = 0.022), and a tendency to a better specificity (81% (78-84%) versus 77% (71-82%), P = 0.065). CONCLUSION: Stress perfusion CMR is highly sensitive for detection of CAD but its specificity remains moderate.

In many visual classification tasks the spatial distribution of discriminative information is (i) non uniform e.g. person `reading' can be distinguished from `taking a photo' based on the area around the arms i.e. ignoring the legs and (ii) has intra class variations e.g. different readers may hold the books differently. Motivated by these observations, we propose to learn the discriminative spatial saliency of images while simultaneously learning a max margin classifier for a given visual classification task. Using the saliency maps to weight the corresponding visual features improves the discriminative power of the image representation. We treat the saliency maps as latent variables and allow them to adapt to the image content to maximize the classification score, while regularizing the change in the saliency maps. Our experimental results on three challenging datasets, for (i) human action classification, (ii) fine grained classification and (iii) scene classification, demonstrate the effectiveness and wide applicability of the method.

Temporal information retrieval has been a topic of great interest in recent years. Its purpose is to improve the effectiveness of information retrieval methods by exploiting temporal information in documents and queries. In this article, we present a survey of the existing literature on temporal information retrieval. In addition to giving an overview of the field, we categorize the relevant research, describe the main contributions, and compare different approaches. We organize existing research to provide a coherent view, discuss several open issues, and point out some possible future research directions in this area. Despite significant advances, the area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches. Moreover, an effective end-to-end temporal retrieval system that exploits temporal information to improve the quality of the presented results remains undeveloped.

In this paper, we study the problem of recovering sparse or compressible signals from uniformly quantized measurements. We present a new class of convex optimization programs, or decoders, coined Basis Pursuit DeQuantizer of moment p (BPDQ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> ), that model the quantization distortion more faithfully than the commonly used Basis Pursuit DeNoise (BPDN) program. Our decoders proceed by minimizing the sparsity of the signal to be reconstructed subject to a data-fidelity constraint expressed in the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -norm of the residual error for 2 ≤ p ≤ ∞. We show theoretically that, (i) the reconstruction error of these new decoders is bounded if the sensing matrix satisfies an extended Restricted Isometry Property involving the Iρ norm, and (ii), for Gaussian random matrices and uniformly quantized measurements, BPDQ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> performance exceeds that of BPDN by dividing the reconstruction error due to quantization by √(p + 1). This last effect happens with high probability when the number of measurements exceeds a value growing with p, i.e., in an oversampled situation compared to what is commonly required by BPDN = BPDQ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> . To demonstrate the theoretical power of BPDQ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> , we report numerical simulations on signal and image reconstruction problems.

The large deployment of Internet of things (IoT) is actually enabling smart city projects and initiatives all over the world. Objects used in daily life are being equipped with electronic devices and protocol suites in order to make them interconnected and connected to the Internet. According to a recent Gartner study, 50 billion connected objects will be deployed in smart cities by 2020. These connected objects will make the authors’ cities smart. However, they will also open up risks and privacy issues. As various smart city initiatives and projects have been launched in recent years, theyhave witnessed not only the expected benefits, but the risks introduced. They describe the current and future trends of smart city and IoT. They also discuss the interaction between smart cities and IoT and explain some of the drivers behind the evolution and development of IoT and smart city. Finally, they discuss some of the IoT weaknesses and how they can be addressed when used for smart cities.

This paper deals with the problem of controlling a hybrid energy storage system (HESS) for electric vehicles. The storage system consists of a fuel cell (FC), serving as the main power source, and a supercapacitor (SC), serving as an auxiliary power source. It also contains a power block for energy conversion consisting of a boost converter connected with the main source and a boost-buck converter connected with the auxiliary source. The converters share the same dc bus, which is connected to the traction motor through an inverter. These power converters must be controlled to meet the following requirements: 1) tight dc bus voltage regulation, 2) perfect tracking of the SC current to its reference, and 3) asymptotic stability of the closed-loop system. A nonlinear controller is developed, on the basis of the system nonlinear model, making use of Lyapunov stability design techniques. The latter accounts for the power converters' large-signal dynamics and for the FC nonlinear characteristics. It is demonstrated using both a formal analysis and simulations that the developed controller meets all desired objectives.

Internet of Things (IoT) is an emerging paradigm that is turning and revolutionizing worldwide cities into smart cities. However, this emergence is accompanied with several cybersecurity concerns due mainly to the data sharing and constant connectivity of IoT networks. To address this problem, multiple Intrusion Detection Systems (IDSs) have been designed as security mechanisms, which showed their efficiency in mitigating several IoT-related attacks, especially when using deep learning (DL) algorithms. Indeed, Deep Neural Networks (DNNs) significantly improve the detection rate of IoT-related intrusions. However, DL-based models are becoming more and more complex, and their decisions are hardly interpreted by users, especially companies&#x2019; executive staff and cybersecurity experts. Hence, the corresponding users cannot neither understand and trust DL models decisions, nor optimize their decisions (users) based on DL models outputs. To overcome these limits, Explainable Artificial Intelligence (XAI) is an emerging paradigm of Artificial Intelligence (AI), that provides a set of techniques to help interpreting and understanding predictions made by DL models. Thus, XAI enables to explain the decisions of DL-based IDSs to make them interpretable by cybersecurity experts In this paper, we design a new XAI-based framework to give explanations to any critical DL-based decisions for IoT-related IDSs. Our framework relies on a novel IDS for IoT networks, that we also develop by leveraging deep neural network, to detect IoT-related intrusions. In addition, our framework uses three main XAI techniques (i.e., RuleFit, Local Interpretable Model-Agnostic Explanations (LIME), and SHapley Additive exPlanations (SHAP)), on top of our DNN-based model. Our framework can provide both local and global explanations to optimize the interpretation of DL-based decisions. The local explanations target a single/particular DL output, while global explanations focus on deducing the most important features that have conducted to each made decision (e.g., intrusion detection). Thus, our proposed framework introduces more transparency and trust between the decisions made by our DL-based IDS model and cybersecurity experts. Both NSL-KDD and UNSW-NB15 datasets are used to validate the feasibility of our XAI framework. The experimental results show the efficiency of our framework to improve the interpretability of the IoT IDS against well-known IoT attacks, and help the cybersecurity experts get a better understanding of IDS decisions.