Lazhar Khelifi

Université de Montréal | UdeM · Department of Computer Science and Operations Research

Motion segmentation in dynamic scenes is currently widely dominated by parametric methods based on deep neural networks. The present study explores the unsupervised segmentation approach that can be used in the absence of training data to segment new videos. In particular, it tackles the task of dynamic texture segmentation. By automatically assign...

Deep learning (DL) algorithms are considered as a methodology of choice for remote-sensing image analysis over the past few years. Due to its effective applications, deep learning has also been introduced for automatic change detection and achieved great success. The present study attempts to provide a comprehensive review and a meta-analysis of th...

Dynamic texture (DT) segmentation, and video processing in general, is currently widely dominated by methods based on deep neural networks that require the deployment of a large number of layers. Although this parametric approach has shown superior performances for the dynamic texture segmentation, all current deep learning methods suffer from a si...

Deep learning (DL) algorithms are considered as a methodology of choice for remote-sensing image analysis over the past few years. Due to its effective applications, deep learning has also been introduced for automatic change detection and achieved great success. The present study attempts to provide a comprehensive review and a meta-analysis of th...

Dynamic texture (DT) segmentation is the problem of clustering into groups various characteristics and phenomena that reproduce in both time and space, assigning a unique label to each group or region. Though this problem is highly complex, it has recently become the focus of considerable interest. This paper presents a simple and effective fusion...

Semantic image segmentation has recently become the focus of considerable interest. This task consists in assigning a predefined class label to each pixel (or pre-segmented region) in an image. To address the complexity challenge of this task, we develop, in this work, a novel and simple energy-minimization model. The proposed cost function of this...

Image segmentation fusion is defined as the set of methods which aim at merging several image segmentations, in a manner that takes full advantage of the complementarity of each one. Previous relevant researches in this field have been impeded by the difficulty in identifying an appropriate single segmentation fusion criterion, providing the best p...

In this paper, we introduce a new fusion model whose objective is to fuse multiple region-based segmentation maps to get a final better segmentation result. The suggested new fusion model is based on an energy function originated from the global consistency error (GCE), a perceptual measure which takes into account the inherent multiscale nature of...

Editeur: Rapport Technique de DIRO n° 1369 RÉSUMÉ. Le réseau social d'entreprise est un outil de partage qui favorise les échanges entre les employés en leur permettant de stocker, de partager, de rendre disponible virtuellement des dossiers et de réaliser un travail d'équipe en temps réel ou différé. Ainsi, les entreprises utilisent les réseaux so...

This paper presents a mathematical model that aims at describing and to resolving the Stochastic DRP with an approach based on the NSGAII. DRP consists in taking the passenger from a place of departure to a place of arrival. The ultimate aim is to offer an alternative to individually and collectively optimized displacements. The DRP is classified a...

This paper describes an application of a Hybrid Algorithm based on the Multi-Objective Simulated AnnealingTabu Search (MOSA-TS) to solve the dynamic Dial a Ride Problem (DRP). In fact, different versions of the dynamic Dial k Ride Problem are found in every day practice; transportation of people in low-density areas, transportation of the handicapp...