Search

Internet of Mobile Things (IoMT) is a new paradigm of the Internet of Things (IoT) where devices are inherently mobile. While mobility enables innovative applications and allows new services, it remains a challenging issue as it causes disconnection of nodes and intermittent connectivity, which negatively impacts the network operation and performance. In addition, energy saving presents a real challenge for networks with limited resources. In this context, a new energy efficient and mobility aware routing protocol called EMA-RPL is proposed based on the well-known Routing Protocol for Low power and Lossy Networks (the RPL standard). Unlike the RPL which is basically designed for static devices, EMA-RPL enables better sustaining of connectivity of mobile nodes and conserving energy. The proposed protocol integrates an enhanced mobility detection method through a continuous control of the distance between the mobile node and its attachment, a novel point of attachment prediction based on the new location of the mobile node, and an efficient replacement strategy preserving the mobile node energy. EMA-RPL overcomes and mitigates problems caused by the mobility of nodes. Simulations using Cooja/Contiki show that EMA-RPL outperforms both the RPL and its mobility aware variant (MRPL) in terms of handover delay, data loss rate, signaling cost and energy consumption.

International audience

Drought disasters significantly affected human life and water resources. Therefore, forecasting methods like statistical models, machine learning, and deep learning architectures help scientists to take effective decisions to decrease the effects of natural disasters by providing decision-making plans. Droughts can be forecasted using meteoro-logical indices like the standardized precipitation evapotranspiration index (SPEI), which aid governments in taking drought-prevention steps. In this paper, we present a big drought architecture for drought modeling and forecasting. The proposed architecture is composed of 5 layers: Data collection, data preprocessing, data storage, data processing and interpretation, and decision making. Besides, we present a comparative study between three different methods ARIMA, PROPHET, and LSTM for drought forecasting. Three different metrics are used for the performance evaluation Root Mean Squared Error (RMSE), coefficient of determination (R2), and Mean Squared Error (MAE). Experiments are carried out using data from the province of Jiangsu. Results revealed that LSTM outperformed the other models, and ARIMA outperformed the PROPHET model.

Monitoring the epidemiological situation of public health remains a challenge, given the exponential growth of health data. Indeed, these latter come from various sources such as, health professionals, biologists, experts in health organizations, etc. In this context, reconciling the search for the greatest amount of appropriate signals and the way of treating them, is the ultimate challenge.

With serious concerns on environmental problems related to CO\(_{2}\) emissions and energy crisis, special attention has recently been paid to Electric Vehicles (EVs). Specifically, an accurate estimation of energy consumption for EV is still a big issue. Therefore, quantifying the impact of various external factors on EV energy consumption, such as road topology, driver profile and traffic conditions is a necessity. In this paper, we review the energy consumption models for EVs. Then, we analyze the impact of the road gradient on EV energy consumption through a set of real world experimentations. The obtained results, allow us to better understand the impact of upward and downward gradient on both energy consumption and energy recuperation processes.

With the rapid growth of image collections, image classification and annotation has been active areas of research with notable recent progress. Bag-of-Visual-Words (BoVW) model, which relies on building visual vocabulary, has been widely used in this area. Recently, attention has been shifted to the use of advanced architectures which are characterized by multi-level processing. Hierarchical Max-Pooling (HMAX) model has attracted a great deal of attention in image classification. To improve image classification and annotation, several approaches based on ontologies have been proposed. However, image classification and annotation remain a challenging problem due to many related issues like the problem of ambiguity between classes. This problem can affect the quality of both classification and annotation results. In this paper, we propose an ontology-based image classification and annotation approach. Our contributions consist of the following: (1) exploiting ontological relationships between classes during both image classification and annotation processes; (2) combining the outputs of hypernym–hyponym classifiers to lead to a better discrimination between classes; and (3) annotating images by combining hypernym and hyponym classification results in order to improve image annotation and to reduce the ambiguous and inconsistent annotations. The aim is to improve image classification and annotation by using ontologies. Several strategies have been experimented, and the obtained results have shown that our proposal improves image classification and annotation.

Today, the existence of several air pollution sources, such as household, transportation and industrial activities, increases the levels of air criteria pollutants in the urban areas and thus causes premature deaths, cardiovascular diseases and acute respiratory infections. To control the pollution levels, wireless technologies, like Wireless Sensor Networks (WSNs), Vehicular Sensor Networks (VSNs) and cellular networks, have become intensively adopted to collect real world data and to transmit decisions to people and interested governments in real time. Within this framework, we developed a new dynamic air pollution monitoring protocol using a communication model dedicated to enable wireless access for mobile objects. Based on Network Simulator 3 (NS-3), the obtained experimental results show that our solution can be applied to control the air data with better performance either in low or high density of vehicles in the regions of interest.

Image hash is an alternative to cryptographic hash functions for checking integrity of digital images. Compared to cryptographic hash functions, an image hash or a Perceptual Hash Function (PHF) is resilient to content preserving distortions and sensitive to malicious tampering. In this paper, a robust and secure image hashing technique using a Gaussian pyramid is proposed. A Gaussian pyramid decomposes an image into different resolution levels which can be utilized to obtain robust and compact hash features. These stable features have been utilized in the proposed work to construct a secure and robust image hash. The proposed scheme uses Laplacian of Gaussian (LOG) and disk filters to filter the low-resolution Gaussian decomposed image. The filtered images are then subtracted and their difference is used as a hash. To make the hash secure, a key is introduced before feature extraction, thus making the entire feature space random. The proposed hashing scheme has been evaluated through a number of experiments involving cases of non-malicious distortions and malicious tampering. Experimental results reveal that the proposed hashing scheme is robust against non-malicious distortions and is sensitive to detect minute malicious tampering. Moreover, False Positive Probability (FPP) and False Negative Probability (FNP) results demonstrate the effectiveness of the proposed scheme when compared to state-of-the-art image hashing algorithms proposed in the literature.

In recent years, the diffusion of electric vehicles(EVs) is of great importance in the road transport and automotive sectors. Reducing electricity consumption and increasing battery autonomy are actually motivating vehicle manufacturers to focus their attention on the EV concept. The evaluation of EV performance through realistic scenarios in traffic simulations is still a key issue. In fact, the road traffic Simulator Simulation of Urban Mobility (SUMO) integrates an energy model for calculating the EV energy consumption. However, this model underestimates the energy consumption values in the real world. In this paper, we intend to investigate the energy consumption models existing in the literature. Then, we assess the performance of the existing energy model in SUMO through a set of simulation scenarios. Finally, we present the main requirements for a realistic, accurate and scalable energy model to estimate the instantaneous energy consumption for EVs.

International audience

Nowadays, Wireless Body Area Networks (WBANs) are revolutionizing the field of healthcare applications which is deeply related to human life and requires a noteworthy attention. In this medical context, reliability, energy consumption and real time monitoring are the main Quality of Service (QoS) challenges to satisfy. This kind of networks relies on wireless channel medium which is sensitive to several factors such as body shadowing, interference, human postures and body signal absorption. In this paper, our main focus is to exploit the knowledge related to the link quality to select the most appropriate Body Node Coordinator (BNC) in order to improve the overall network performance. Our experimental study which is based on real testbeds revealed that the position of the BNC is sensitive to human morphology and practiced activity.

Many studies aim at introducing recent technologies in Electric Vehicles (EVs) to accurately estimate their energy consumption. In this paper, we reviewed the current energy consumption model in SUMO. This latter is known to be the most reliable traffic simulator used for evaluating traffic management and vehicular technologies. We proposed a set of improvements that must be applied on SUMO energy model and we focused on integrating the ambient temperature factor. Finally, simulation results show the accuracy of the proposed solution from different perspectives.

Wireless Body Area Networks are nowadays attracting both academic and industrial worlds. Combining collected data related to patient context with original health measurement can enhance the general health state monitoring and help to better understand the patient disease evolution. Daily activity is one of the important features that may influence the patient health state. Thus, recognizing the user activity can be a useful way for improving quality of health services. Relying on supervised learning, we study the feasibility of extracting and classifying the human activities from channel gain measures, which is an important feature that characterizes the WBAN channel links.

The attempts to reduce vehicle’s CO2 emissions and fuel consumption are actually motivating the manufacturers in the transport and automotive sectors to focus their interests on Electric Vehicle (EV) concept. Battery autonomy and charging process are still a big issue for that kind of vehicles. The evaluation of EV’s instantaneous energy consumption through realistic scenarios and based on consistent energy models are needed to take step forward on these issues. In this paper, we provide a deep insight on EV consumption dynamics and make a review of the energy model implemented in SUMO, one of the most popular traffic simulation framework used to evaluate vehicular technologies and strategies. We propose a set of energy consumption estimation improvements and show through simulation the achieved improvements in terms of accuracy compared to the sumo implementation.

In this paper, we propose a joint power control and resource allocation approach for co-channel deployed high dense small-cells in macro-cell networks, denoted as Two-tier Optimized Resource and Power Allocation approach (TORPA). The ultimate goal of our contribution is to mitigate the co-tier and cross-tier interference faced by indoor and outdoor users in downlink communications and efficiently satisfy their resource requirements. With this in mind, we formulate the resulting optimization problem as a Mixed-Integer Linear Program (MILP) that aims to minimize the total transmit power and achieve an efficient two-tier physical resource allocation. Then, we propose a semi-centralized scheme to solve it. Extensive simulations show that TORPA can efficiently allocate power and distribute spectrum resources to both Small-cell Users (SUs) and Macro-Users (MUs) compared to the distributed resource allocation scheme and a prominent state of the art gametheoretic approach. In particular, TORPA improves the SU’s throughput by up to 9 times and 22% in comparison to these both schemes.

Workflows management systems (WfMS) are aimed for designing, scheduling, executing, reusing, and sharing workflows in distributed environments like the Cloud computing. With the emergence of e-science workflows, which are used in different domains like astronomy, life science, and physics, to model and execute vast series of dependents functionalities and a large amount of manipulated data, the workflow management systems are required to provide customizable programming environments to ease the programming effort required by scientists to orchestrate a computational science experiment. A key issue for e-science WfMS is how to deal with the change of the execution environment constraints and the variability and confliction of end users and cloud providers objectives for the execution of the same workflow or sub-workflow. They have to customize their management processes to insure the adaptability of the execution environment to the scientific workflows specificities, especially when dealing with large-scale (data, computing, I/O)-intensive workflows. In this paper, we propose a dynamically re-configurable framework for the deployment of scientific workflows in the Cloud (called DR-SWDF) that allows customizing the workflow deployment process according to a set of objectives and constraints of end users or cloud providers defined differently for the tasks or partitions of the same workflow. The DR-SWDF framework offers a K-means based algorithm that allows dynamically clustering the input workflows or sub-workflows in order to identify the most convenient techniques or algorithms to be applied for their scheduling and deployment in the cloud. The simulations results run on three examples large-scale scientific workflows show that our proposed framework can achieve better results than the use of a generic purpose approach.

Wireless sensor networks (WSNs) are widely used nowadays in various domains. In general, the applications in which the WSN is deployed need that this network presents a minimal degree of reliability, effectiveness and robustness. However, the specificity of the nodes deployed in this type of networks makes them prone to failures. In this paper, we discuss the recovery from simultaneous failures for a large scale WSN in a multichannel context. Indeed, we propose a deployment scenario which uses thousands of sensor nodes and relay nodes. Then, we propose Simultaneous Failure Recovery based on Relay Node Relocation (SFR-RNR) approach which aims to recover from simultaneous failures. These failures lead to the damage of a whole segment of the WSN, and hence, the loss of the monitored field coverage and/or connectivity. SFR-RNR rearranges a minimal set of relay nodes to restore, partially, the coverage and improve or restore the connectivity; then it reallocates the channels to minimize the interferences. The performance of the proposed approach is evaluated by simulation.

International audience; In this paper, we investigate intelligent handoff decisions in femtocell networks, with the goal of achieving a seamless femtocell-to-femtocell handoff procedure that minimizes unnecessary handoffs and provides a good quality of connection to mobile users. To this aim, we propose a promising handoff scheme called Optimized Handoff based on Mobility Prediction and Call Admission Control (OHMP-CAC). Our proposal is based on a next cell prediction module using an efficient Hidden Markov Model (HMM) predictor on one hand, and a Call Admission Control (CAC) algorithm with service differentiation for applications with and without QoS constraints, on the other hand. To gauge the effectiveness of our proposal, we conducted extensive simulations based on real human mobility traces. Results show that OHMP-CAC outperforms existing approaches in terms of the number of handoffs, the dwell time, and the handoff decision time, while providing a connection with excellent quality of signal to femtocell user equipments (UE).

International audience; Dans cet article nous proposons une nouvelle méthode d'allocation distribuée des canaux pour le réseau de capteurs a radio cognitive déployé pour les réseaux électriques de distribution dits smart grids (SG). La solution permet d'éviter l'accès égoïste des capteurs pour la transmission des données tout en respectant l'hétérogénéité du trafic généré et sans l'utilisation d'un canal de contrôle en commun (CCC). La solution proposée est évaluée par l'outil de la simulation qui montre sa capacité a réaliser une allocation équitable des ressources spectrales sans l'utilisation d'un élément central.

Cloud Computing has emerged as a service model that enables on-demand network access to a large number of available virtualized resources and applications with a minimal management effort and a minor price. The spread of Cloud Computing technologies allowed dealing with complex applications such as Scientific Workflows, which consists of a set of intensive computational and data manipulation operations. Cloud Computing helps such Workflows to dynamically provision compute and storage resources necessary for the execution of its tasks thanks to the elasticity asset of these resources. However, the dynamic nature of the Cloud incurs new challenges, as some allocated resources may be overloaded or out of access during the execution of the Workflow. Moreover, for data intensive tasks, the allocation strategy should consider the data placement constraints since data transmission time can increase notably in this case which implicates the increase of the overall completion time and cost of the Workflow. Likewise, for intensive computational tasks, the allocation strategy should consider the type of the allocated virtual machines, more specifically its CPU, memory and network capacities. Yet, a critical challenge is how to efficiently schedule the Workflow tasks on Cloud resources to optimize its overall quality of service. In this paper, we propose a QoSaware algorithm for Scientific Workflows scheduling that aims toimprove the overall quality of service (QoS) by considering the metrics of execution time, data transmission time, cost, resources availability and data placement constraints. We extended the Parallel Cat Swarm Optimization (PCSO) algorithm to implement our proposed approach. We tested our algorithm within two sample Workflows of different scales and we compared the results to those given by the standard PSO, the CSO and the PCSO algorithms. The results show that our proposed algorithm improves the overall quality of service of the tested Workflows.

Wireless sensor networks (WSNs) are widely used nowadays and in a various domains. However, the specificity of the nodes deployed in this type of networks makes them prone to failures. To overcome this problem and guarantee the continuity of the network functioning even in the presence of node failure, fault tolerance mechanisms need to be designed and integrated to the operation of those networks. These fault tolerance mechanisms will more precisely deal with recovering from a failures and resuming the correct functioning of a WSN. With that aim, we propose in this paper a new centralized curative approach, called Rotating Nodes based Failure Recovery (RNFR), dedicated to restore connectivity in multi-channel WSNs. The proposed solution targets the failure of particular nodes designated as articulation nodes, which leads to the partitioning of the WSN into many segments isolated from each other and leading to connectivity loss. Therefore, the main tasks of RNFR are the restoration of the connectivity after an articulation node failure using reorganization and reallocation of channels. Moreover, the solution uses a node rotation technique to communicate the recovery information to all the disjoint parts of the network. The proposed approach proved to be interesting by giving motivating results while evaluated through simulation.

Fault tolerance is one of the most important wireless sensor networks requirements. It ensures that the network continues to function correctly even when some components fail. In fact, fault tolerance is a need in this type of networks due to sensor node characteristics, radio communications and hostile environments in which these networks are deployed. In this survey, we give an overview of WSN mechanisms that provide or improve the fault tolerance property of wireless sensor networks. However, the different solutions presented in this survey are not only intended to mechanisms dedicated to fault tolerance, but they also include all the mechanisms allowing the prevention of fault occurrence such as energy aware routing and data aggregation and compression. Besides the classification of fault tolerance mechanisms according to the tasks they target (data management, flow management), we also propose a new classification based on the network size, since the performance of the majority mechanisms depends on the size in terms of geographical area and number of nodes. Thus, a well performing protocol conceived for small networks may be inadequate for large networks and vice versa.

International audience

International audience; Nowadays, Normalized Difference Vegetation Index (NDVI) time-series has been successfully used in research regarding global environmental change. NDVI time series have proven to be a useful means of indicating drought -related vegetation conditions, due to their real-time coverage across the globe at relatively high spatial resolution. In this paper, we propose a method for detecting rare events in NDVI series. These events are particularly rare and infrequent which increases their complexity of detecting and analyzing them. The proposed method is based on the analysis of the random component by Jarque-Bera test to verify the presence of rare events and obtain their features (time and amplitude). For validation, we have used a database for regions in Northwestern of Tunisia. These data come from MODIS for a period from 18 February 2000 to 17 November 2013 at a spatial resolution of 250 m by 250m.

One of the common challenges in Wireless Sensor Networks (WSNs) is the degradation of the performance due to several factors. In one hand, the interference between concurrent transmissions can affect the efficiency of the network and considerably degrades its performance. The exploitation of the multiple channels available in sensor technology and the development of protocols for WSNs can be a solution to mitigate this interference. In this case, the way the channels are assigned has a significant impact on the performance of multi-channel communication. In the other hand, the faults occurred in WSNs are another factor that degrades the WSN performance. In this paper, we propose a distributed energy-efficient solution for multi-channel allocation based on the routing. This solution implements a fault recovery mechanism to reconnect the network after an articulation node failure. A main task of the proposed approach is to minimize the number of interferences when allocating the limited number of available channels. As a second task, the approach minimizes the energy consumption by defining a sleeping/activity strategy. The fault recovery mechanism aims to restore the network connectivity and reallocate channels without affecting the whole WSN. The performance of the proposed solution is evaluated by simulation.

Scalability is a key issue for Multi-Agent Systems (MAS) that aim to model and simulate complex systems. Distributed infrastructures such as clusters, grids and clouds are powerful computational environments that can be effectively used to run large-scale agent-based simulations. To properly distribute an agent-based system and ensure its performance, an appropriate partitioning approach is required. Although multiple partition methods for distributed MAS exist, they remain specific to the individual requirements of a given application domain. There is no generic approach for guiding the designers and developers to select an appropriate approach for partitioning a given agent-based system. Thus a recurrent challenging task, for MAS designers and developers, is how to evaluate, select and then apply the appropriate partitioning mechanism for a given MAS. Therefore, in this paper, we present a generic conceptual framework useful to analyze existing partitioning methods. It can also be used as a basis while designing a distributed architecture of new MAS.

International audience

International audience

In Wireless Sensor Networks, low latency, energy efficiency, and coverage problems are considered as three key issues in designing routing protocols. In this paper we present a new protocol called Low Energy Adaptive Tier Clustering Hierarchy (LEATCH), which offers a good compromise between delay and energy consumption and resolves some coverage problems. For our purpose, a two level hierarchical approach has been proposed to organize a sensor network into a set of clusters, every cluster divided into small clusters that are called Mini Clusters. As the way the clusters are organized, for each mini cluster we define a Mini Cluster- Head (MCH). Every MCH communicates with the cluster-head directly, it aggregates its mini-cluster information. In addition, we have made some changes in the procedure of cluster head and mini cluster head election. LEATCH promises better performances than the conventional LEACH protocol which is one of the most known hierarchical routing protocols using the probabilistic model to manage the energy consumption in WSNs. Simulation results show that LEATCH performs better than LEACH in term of energy, delay, coverage and scalability.

International audience

International audience; Nowadays, the process of change detection is regarded as an outstanding way for urban planning and design. The major concern of this paper is to investigate the nonstationary character of multi-temporal time series. To overcome this problem, we propose an adaptive multiplicative decomposition of non-stationary multi-temporal satellite image, which allows to decompose the series into three components: trend, seasonal and random, to properly model the evolution of land cover. We carried several experiments to validate our approach based on Landsat images covering the region of "Tres Cantos-Madrid" in Spain. The obtained results show the effectiveness of our proposed method comparing to some conventional methods.

Cloud Computing is emerging today as a service model used to relocate locally-based data and applications to virtualized services available via Internet at a lower cost. A key to exploit the benefits of this model is orchestration which consists in coordinating effectively the deployment of a set of virtualized services in order to fulfill operational and quality objectives of end users and Cloud providers. Cloud orchestration can be carried out at two levels: hardware level orchestration and software level orchestration. In this paper, we highlight the main challenging points about the Cloud orchestration concept. Then, we carry on a comparative study of some existing research works involved with this concept at hardware and software levels.

One of the most common needs in wireless sensor networks (WSNs) is the continuity of network function even in the presence of some node failures. This is called fault tolerance. In general, fault tolerant solutions can be preventive or reactive: the preventive techniques aim to prevent the failure by minimizing and balancing the energy consumption in each node, while the reactive techniques intervene after a failure was detected. In this paper, we propose a new preventive/reactive fault tolerant scheme dedicated to manage the energy consumption and reconnect the WSN in case of articulation node failure. The specificity of this scheme is the use of multichannel communications, allowing simultaneous data transmission, which decreases the interferences between nodes and then decreases data retransmissions. The second task of this scheme targets the reorganization of the network after a network portioning episode. Such episode means that the WSN is partitioned in many segments after an articulation node failure. More precisely, we present here two heuristics for channel allocation/reallocation and WSN reorganization after a network failure. The performances of the proposed scheme is evaluated and proved through simulation.

International audience; In this paper, we propose a methodology for changes prediction in urban area using Hidden Markov Model (HMM). The main focus is to study a non- stationarity data in HMM models. In order to use these data we apply a stationarity processes. We propose to calculate a spatial metrics of in urban area from satellite images. Then, a stationnarisation process was applied to remove the random variations, and to model the variations by using HMM. A comparative study is done. The performance of our method is showed by using a series of Landsat.

International audience; no abstract

International audience

Nowadays remote sensing is an important technique for observing Earth surface applied to different areas such as, land use, urban planning, remote monitoring, real time deformation of the soil that can be associated with earthquakes or landslides, the variations in thickness of the glaciers, the measurement of volume changes in the case of volcanic eruptions, deforestation, etc. To follow the evolution of these phenomena and to predict their future states, many approaches have been proposed. However, these approaches do not respond completely to the specialists who process yet more commonly the data extracted from the images in their studies to predict the future. In this paper, we propose an innovative methodology based on hidden Markov models (HMM). Our approach exploits temporal series of satellite images in order to predict spatio-temporal phenomena. It uses HMM for representing and making prediction concerning any objects in a satellite image. The first step builds a set of feature vectors gathering the available information. The next step uses a Baum-Welch learning algorithm on these vectors for detecting state changes. Finally, the system interprets these changes to make predictions. The performance of our approach is evaluated by tests of space-time interpretation of events conducted over two study sites, using different time series of SPOT images and application to the change in vegetation with LANDSAT images.

The work developed in the context of this article stems from the thesis work in progress (done in RIADI labs. at the National School of Computer Sciences, Tunisia in collaboration with the Research Unit of Evaluation of Automated Transport Systems and Safety IFSTTAR, French). The works treat the problem of knowledge management of a critical area, that of security and in particular the railroad accidents. The goal is to provide methodological support and tools to support the capitalization and exploitation of produced knowledge and/or used by domain experts. We have proposed an approach based on domain ontology and Case-based Reasoning CBR. We will present as part of this article, the first realized works in our approach.

International audience

The work presented in the context of this paper is to develop a system of Case-Based Reasoning (CBR) to help capitalize and exploit the knowledge on railroad accidents from our field of application. To streamline and strengthen the acquisition process, representation and exploitation of this domain knowledge, initially, it is necessary to harmonize and standardize the terminology used by the domain actors. In this context, we have agreed to call on building ontologies. Far from being just an effect of "fashion" or a goal in itself, ontology finds its place in resolving problems. For this purpose, ontologies can play an important role in the CBR systems, because they can greatly reduce the effort of acquiring knowledge in various stages of reasoning. In this paper, we will present the first realized works in our approach.

International audience

Relaying on a virtual backbone formed by the induced hierarchy of a connected dominating set is a widespread solution in ad hoc networks. However, the majority of existing approaches require gathering neighborhood information without considering the loss of information due to collision and the effect of wireless interference and its impact on the accuracy of information used during clustering process. In this paper, we present an improved version of our clustering algorithm, TBCA, operating in layered manner and exploiting the eventual collision to accelerate the clustering process. We prove through simulations that our mechanism outperforms other ones, in terms of effectiveness throughput and per-packet sojourn delay. Conducted simulations show also that it copes better with mobility.

National audience

International audience; We propose in this paper a search approach which aim to improve identification in biometric databases. We work with face images and we develop appearance-based Eigenfaces method to generate holistic and discriminant features. These feature vectors, which describe faces, are often used to establish the required identity in a recognition process. In this work, we introduce a clustering process which aims to split biometric databases into partitions and to simplify consequently recognition task within these databases. Various studies were undertaken on search strategies to adjust feature extraction and clustering parameters. We simulate four experts which learn differently and acquire various knowledge to recognize facial images. In addition, we evaluate the robustness and the performance of our approach against noise effect through different test series. We propose, finally, to combine and to fuse clustering classifiers and identification processes what improve and simplify our recognition system task.

This work deals with unsupervised change detection in bi-date Synthetic Aperture Radar (SAR) images. Whatever the indicator of change used, e.g. log-ratio or Kullback-Leibler divergence, we have observed poor quality change maps for some events when using the Hidden Markov Chain (HMC) model we focus on in this work. The main reason comes from the stationary assumption involved in this model − and in most Markovian models such as Hidden Markov Random Fields−, which can not be justified in most observed scenes: changed areas are not necessarily stationary in the image. Besides the few non stationary Markov models proposed in the literature, the aim of this paper is to describe a pragmatic solution to tackle stationarity by using a sliding window strategy. In this algorithm, the criterion image is scanned pixel by pixel, and a classical HMC model is applied only on neighboring pixels. By moving the window through the image, the process is able to produce a change map which can better exhibit non stationary changes than the classical HMC applied directly on the whole criterion image. Special care is devoted to the estimation of the number of classes in each window, which can vary from one (no change) to three (positive change, negative change and no change) by using the corrected Akaike Information Criterion (AICc) suited to small samples. The quality assessment of the proposed approach is achieved with speckle-simulated images in which simulated changes is introduced. The windowed strategy is also evaluated with a pair of RADARSAT images bracketing the Nyiragongo volcano eruption event in January 2002. The available ground truth confirms the effectiveness of the proposed approach compared to a classical HMC-based strategy.

International audience

International audience

International audience; In this paper, we present a new face recognition approach based on dimensional surface matching. While most of existing methods use facial intensity images, a newest ones focus on introducing depth information to surmount some of classical face recognition problems such as pose, illumination, and facial expression variations. The presented matching algorithm is based first on ICP (Iterative Closest Point) that align rigidly facial surfaces and provides perfectly the posture of the presented probe model. Second, the similarity metric consists in computing geodesic maps on the overlapped parts of the aligned surfaces.The general paradigm consists in building a full 3D face gallery using a laser-based scanner (the on-line phase). At the on-line phase of identification or verification, a captured 2.5D face model (range image) is performed with the whole set of 3D faces from the gallery or compared to the 3D face model of the genuine, respectively. This probe model can be acquired from arbitrary viewpoint, with arbitrary facial expressions, and under arbitrary lighting conditions. Finally, We discuss some experimental results done on the ECL-IV2 new 3D face database.

A novel method of parametric active contours with geometric shape prior is presented in this paper. The main idea of the method consists in minimizing an energy functional that includes an additional information on a shape reference called "template" or "prototype". Prior shape knowledge is introduced throw a complete family of Euclidean invariants, computed from the Fourier descriptors of the evolving contour and the prototype. It enhances the model robustness to noise and occlusion, and allows it to evolve in highly concave boundaries. The variational formulation of the proposed approach is described in details. Experimental results on both synthetic and real images are presented and discussed.

International audience