Brahim Farou

Université 8 mai 1945 - Guelma · Department of Computer Science

The coronavirus disease (COVID-19) pandemic, originating in Wuhan, China, in 2019, has spread to over 200 countries, posing a significant burden on global health systems and the global economy. The urgent need for faster and more accessible diagnostic methods has become evident, especially in regions with limited resources. Early detection can help...

Nowadays, to ensure people’s and property’s safety, cities have dozens of cameras installed on almost every corner. However, the haphazard deployment of these cameras often results in overlapping fields of view, leading to redundant processing of the same events by multiple cameras. This situation requires more power, huge bandwidth, and more stora...

In real-time object tracking systems, it is essential to assign a unique identifier or label to each tracked object to distinguish it from other objects to reduce the number of ID switching (ID-Sw) and improve tracking quality. To perform the object labeling process, massive metadata must be researched to determine the appropriate label. Despite th...

Internet of Things (IoT) systems include many smart devices that continuously generate massive spatio-temporal data, which can be difficult to process. These continuous data streams need to be stored smartly so that query searches are efficient. In this work, we propose an efficient method, in the fog-cloud computing architecture, to index continuo...

The rise of IoT has led to an increase in drone usage. Losing connection with a drone during a mission can be dangerous, particularly in tasks like search and rescue or surveillance. The current recovery systems for lost drones can only retrieve the drone after it crashes, which endangers mission success and data confidentiality. Moreover, IoT netw...

In recent years, the large amount of heterogeneous data generated by the Internet of Things (IoT) sensors and devices made recording and research tasks much more difficult, and most of the state-of-the-art methods have failed to deal with the new IoT requirements. This article proposes a new efficient method that simplifies data indexing and enhanc...

The continuous production of heterogeneous IoT data created a new challenge, which is their storage and retrieve efficiently. In this work, a new method of indexing, called Threshold Distance (TD), is proposed in the fog‐cloud architecture. In this method, the fog layer is divided into two levels: a clustering level and an indexing level. In the cl...

Unmanned Aerial Vehicles (UAVs) have been progressively used in environmental monitoring and disaster sensing. The drones fly over a set of waypoints in the area to achieve their surveillance task. Despite their potential advantages, UAVs have several drawbacks, including a limited energy supply and a short operational duration which make all attem...

This paper addresses the issue of the real-time tracking quality of moving objects in large-scale video surveillance systems. During the tracking process, the system assigns an identifier or label to each tracked object to distinguish it from other objects. In such a mission, it is essential to keep this identifier for the same objects, whatever th...

The past decade has been characterized by the growing volumes of data due to the widespread use of the Internet of Things (IoT) applications, which introduced many challenges for efficient data storage and management. Thus, the efficient indexing and searching of large data collections is a very topical and urgent issue. Such solutions can provide...

Real-time object tracking is still a critical challenge in artificial vision research. In such a mission, it is essential to assign a unique identifier or label to each tracked object, regardless of the area, time of appearance, or detector camera, to distinguish it from other objects and to conserve as much information as possible about the tracke...

IoT technology implies a huge group of connected devices to capture a tremendous quantity of information. Computing and storing this huge amount of data requires scalable and efficient indexing solutions. Among the latest indexing structures in the BCCF-tree metric space, one framework is focused on providing recursive clustering of the space using...

Artificial Immune Recognition System is a widely used bio-inspired algorithm that describes the recognition tasks of antigen by memory cells. Despite the success of the Artificial Immune Recognition System, the basic version has some drawbacks which have a direct impact on system efficiency in terms of the quality of the results, data explosion, an...

Over the past decades, the volume of Internet of Things (IoT) data has exploded which raise the problem of indexing, storing and retrieving efficiently. Most studies are based on dividing the target dataset into subsets using balls with one or two pivots. However, in the era of big data, where efficient indexing is important, the subspace volumes g...

AM conference is the leading forum for research in informatics and applied mathematics. The third edition organized and sponsored by LabSTIC Laboratory held on virtual mode on October 21-22, 2020 at 08 May 1945 University in Guelma. As the previous editions IAM’18 and IAM’19, it offers an excellent forum for researchers and practitioners from vario...

Background subtraction is an essential step in the video monitoring process. Several models have been proposed to differentiate background pixels from foreground pixels. However, most of these methods fail to distinguish them in highly dynamic environments. In this paper, we propose a new method robust and more efficient for distinguishing moving o...

CITSC Aims to bring together the scientists, young and senior researchers to propose their ideas, contributions and to exchange and share their experiences and research results on all aspects of Innovative Trends in Computer Science. It also provides a premier platform for researchers, practitioners and educators to present and discuss the most rec...

In recent years, the number of sensor and actuator nodes in the Internet of Things (IoT) networks has increased, generating a large amount of data. Most research techniques are based on dividing target data into subsets. On a large scale, this volume increases exponentially, which will affect search algorithms. This problem is caused by the inheren...

Wireless multimedia sensor networks (WMSNs) currently face the problem of rapidly decreasing energy due to the acquisition, processing and transmission of massive multimedia data. This decrease in energy affects the life of the network, resulting in higher overhead costs and a deterioration in quality of service (QoS). This paper presents a new gro...

In order to improve safety and security in the public areas, researchers are setting up several smart cameras such Unmanned Aerial Vehicles UAVs (also called drones) in major cities. Faced to this growing number of cameras, the covering, and the tracking of disasters without a monitoring process of the cameras become very difficult task for human o...

The diversity in background scenes such as, illumination changes, dynamics of the background, camouflage effect, shadow, etc. is a big deal for moving objects detection methods makes it impossible to manage the multimodality of scenes in video surveillance systems. In this paper we present a new method that allows better detection of moving objects...

Background subtraction is an essential step in the process of monitoring videos. Several works have proposed models to differentiate the background pixels from the foreground pixels. Mixtures of Gaussian (GMM) are among the most popular models for a such problem. However, the use of a fixed number of Gaussians influence on their results quality. Th...

Tracking of moving objects is a very important step in building an intelligent video surveillance system. The movement of non-rigid objects, appearance variations and luminosity changes make tracking even more difficult. This paper proposes a new automatic multi-target tracking system that can deal with the most confronted problems without any prio...

Tracking of moving objects is a very important step in building an intelligent video surveillance system. The movement of non-rigid objects, appearance variations and luminosity changes make tracking even more difficult. This paper proposes a new automatic multi-target tracking system that can deal with the most confronted problems without any prio...

Over the past decade, a large amount of data has been generated exponentially by an increasing number of devices in the Internet of Things (IoT) world. This explosion has created the need to create data processing systems capable of managing these huge volumes of data and offering high-performance solutions in order to make the most of this mass of...

Background subtraction is an essential step in the process of monitoring videos. Several works have proposed models to dierentiate the background pixels from the foreground pixels. Mixtures of Gaussian (GMM) are among the most popular models for a such problem. However, they suer from certain inconveniences related to the light variations and compl...

Background subtraction is an essential step in the process of monitoring videos. Several works have proposed models to dierentiate the background pixels from the foreground pixels. Mixtures of Gaussian (GMM) are among the most popular models for a such problem. However, they suer from certain inconveniences related to the light variations and compl...

In this paper, we present a new method of clustering cameras in the wireless multimedia sensor network based on overlapping camera fields of view. In this method, we try to group as many overlapping cameras as possible together using the Bron-Kerbosch algorithm that allows us to find maximum cliques, where they represent camera clusters with strong...

The cirrus clouds is one of the objects existing in the troposphere how play an important role in the process of climate change. The research presented in this paper is aimed to present a model for detecting of clouds, presenting theirs distributions and giving a measure about altitudes by a stereovision system. Two cameras simultaneously take imag...

Searching for similar images in a data collection, based on a query image is a fundamental problem for many applications that use large amounts of complex data. The search for images by its content and on a large scale is a topical challenge for the search and management of large image databases. Several information can be extracted such as color,...

The cirrus clouds is one of the objects existing in the troposphere how play an important role in the process of climate change. The research presented in this paper is aimed to present a model for detecting of clouds, presenting theirs distributions and giving a measure about altitudes by a stereovision system. Two cameras simultaneously take imag...

Thanks to the technological development of the Internet and communication that the world has experienced in recent years, researchers have proposed several strategies to address the weaknesses of traditional video surveillance systems where they are becoming continuous and high-performance. Among these strategies, the one that is most used and effe...

In this paper, we propose an off-line system for the segmentation and recognition of the unconstrained handwritten connected digits. The proposed system provides new segmentation paths by finding two types of structural features. The background and foreground features points are found from the input string image. The possible cutting paths are gene...

Moving cast shadow removal is an important task in computer vision, which is used after foreground segmentation to improve the tracking performance. The existing approaches, in terms of ability in discrimination between shadows and foreground object, remain inaccurate. In this paper, a new system is proposed to detect the shadow of moving objects i...

We present in this paper a novel and efficient method that will significantly reduce GMM drawbacks in the presence of complex and dynamic scene. The main idea is to combine global and local features to remove local variations and the instant variations in the brightness that, in most cases, decrease the performance of background subtraction models....

Le suivi des objets en mouvement est une étape essentielle pour construire un système intelligent de prise de décision précis et rapide. Cependant, il y a plusieurs conditions rendent le suivi d'objet difficile. Ces conditions incluent le mouvement d'objet non-rigide, les variations d'apparence de cibles dues à des changements d'illumination, et l'...

Cast shadow affects computer vision tasks such as image segmentation, object detection and tracking since objects and shadows share the same visual motion characteristics. This unavoidable problem decreases video surveillance system performance. The basic idea of this paper is to exploit the evidence that shadows darken the surface which they are c...

Cast shadow affects computer vision tasks such as image segmentation, object detection and tracking since objects and shadows share the same visual motion characteristics. This unavoidable problem decreases video surveillance system performance. The basic idea of this paper is to exploit the evidence that shadows darken the surface which they are c...

Nous avons proposé dans ce papier un système de suivi des objets en mouvement à travers une caméra fixe. Le système utilise une combinaison entre la classification, l'apprentissage et le suivi. L'apprentissage en ligne, avec les don-nées étiquetées et les données non étiquetées, a permis d'augmenter la fiabilité du classifieur grâce à un mécanisme...

Dans ce travail, une nouvelle méthode pour la segmentation des chiffres manuscrits connectés a été proposée. Cette méthode est basée sur l’extraction de deux types de caractéristiques structurelles dans l’image de chaînes de chiffres. Le but de la combinaison de ses deux caractéristiques est de prendre les meilleurs chemins de segmentation entre le...

Extraction of moving objects is a key step in a visual surveillance area. Many background models have been proposed to resolve this problem, but Gaussian Mixture Model (GMM) remains the most successful approach for background subtraction. However, the method suffers from Sensitivity (SE) to local variations; variations in the brightness and backgro...

The presence of dynamic scene is a challenging problem in video surveillance systems tasks. Mixture of Gaussian (MOG) is the most appropriate method to model dynamic background. However, local variations and the instant variations in the brightness decrease the performance of the later. We present in this paper a novel and efficient method that wil...

In order to improve safety and security in public and private places, senior responsible have taken radical steps by implementing hundreds of surveillance cameras in major cities. Faced with this growing number of emerged cameras by a desire to acquire CCTV systems and the low cost camera equipment, management of monitoring stations has become a he...

In video surveillance, many promising approaches for detecting cast shadow of moving objects are available in literature survey. Most of works devoted in this field are inaccurate in terms of ability to distinguish between shadows and foreground object. The purpose of this paper is to propose a new system that is characterized both by its quality a...

Despite the large number of promising approaches existing, it's still a hard work to obtain desirable results in the area of people detection, especially in terms of time. In this paper, we present a real-time and accurate human detector for video surveillance system, which includes background subtraction technique to extract candidate region, CENT...

Despite the large number of promising approaches existing, it's still a hard work to obtain desirable results in the area of people detection, especially in terms of time. In this paper, we present a real-time and accurate human detector for video surveillance system, which includes background subtraction technique to extract candidate region, CENT...

Preface Ces actes regroupent les articles présentés lors des quatrièmesJournées Doctorales en Informatique (JDI'2014) qui se sont déroulées les 03-04 Décembre 2014 à l'Université 8 Mai 1945 de Guelma, Algérie. JDI est une manifestation scientifique qui a pour objectifs de regrouper les jeunes thésards en informatique avec leurs différentes probléma...

Ces actes regroupent les articles présentés lors des 3èmes Journées Doctorales en Informatique (JDI'2013) qui se sont déroulées les 04-05 Décembre 2013 a l’Université 8 Mai 1945 de Guelma, Algérie. JDI est une manifestation scientifique qui a pour objectifs de regrouper les jeunes thésards en informatique avec leurs différentes problématiques de re...

We present in this paper a system for detecting moving objects in video surveillance. We used a new approach for background substraction based on Gaussian mixtures and the HSV color space. On the one hand, the RGB space does not represent the influence of light on color because it affects all three components. On the other hand, local variations, v...

We propose in this paper a background subtraction system for image sequences extracted from fixed camera using Gaussian Mixture Models (GMM) and the analysis of color histograms. This system can achieve best accuracy than a simple GMM while maintaining the same computational resources. Images extracted from the video will first be divided into seve...

The widespread use of video surveillance and the development of embedded information processing systems raise the issue of affecting the confidentiality and integrity of video data and even the privacy of individuals. In order to secure the content of video and protect the privacy of the public, we propose a system for detecting, tracking and encry...

This paper presents the possibility of using image completion combined with a large image database to create an infinite panorama. Existing methods employ extending textures found in the input source image, into the unknown region. Such methods do not work in this case since the neighboring scene will almost never be a simple extension of the curre...

we present in this paper a system for extracting moving objects in video surveillance modeling based on Gaussian Mixture Models (GMM) and the analysis of color histograms. systems based on GMM feel pain from performance degradation in the presence of local variations, variations in brightness as well as the complexity of the background. To remedy t...

. La détection automatique des objets en mouvement est une tâche très importante dans les systèmes de vidéo de surveillance. Les anciens systèmes basés sur les compétences des agents de sécurité ont montré leurs limites. Effectivement, beaucoup de séquences visuelles importantes peuvent leur échapper. Pour cela un système de vidéo surveillance s’im...

Dans ce papier, nous présentons un système de reconnaissance de l’écriture manuscrite arabe utilisant les modèles de Markov cachés (MMC) et les réseaux neuronaux (RN) dans une architecture probabiliste en tirant avantage des deux outils. Le classifieur MMC va générer une liste des N meilleures hypothèses de mots ainsi que leurs segmentations en car...

Les Modèles de Markov Cachés ont eu beaucoup de succès avec le domaine de la reconnaissance (texte, image et parole), ce succès vient de leur capacité d'intégration du contexte et d'absorption du bruit. Dans ces modèles les formes sont décrites par une séquence de caractéristiques qui seront observées dans les états du modèle. Cependant, les inform...