جستجوی استاد راهنمای دانشگاهی

Lâmân LELÉGARDمشاهده پروفایل

پژوهشگر

• Image Processing
• Photogrammetry
• Remote Sensing
• +۳ مورد دیگر

Lâmân LELÉGARD serves as a Researcher at the French National Institute of Geographic and Forest Information (IGN), currently assigned to the MATIS laboratory since 2018 after 10 years at LASTIG. As a Civil Servant Engineer and member of the GEOVIS research team, he contributes to geospatial research while occasionally teaching image processing, DTM manipulation, and colorimetry courses in the PPMD Master's program at the National School of Geographic Sciences (ENSG). His academic foundation includes an engineering degree (2004-2007) and Specialized Master in Geodesy (2006-2007) from ENSG, preceded by Mathematics and Physics preparatory classes at Charlemagne High School (2001-2004). Early career internships involved gravitational field analysis at Belgium's Royal Observatory (2006) and gravito-elastic equations at Paris Institute of Earth Physics (2007). LELÉGARD's research centers on image quality enhancement in photogrammetry, with sustained contributions to motion blur correction, radiometric processing, and colorimetry. His work addresses practical challenges in aerial/terrestrial imagery, including nighttime scanning systems, channel-dependent exposure artifacts, and scanned campaign inhomogeneities. Methodologies leverage adaptive filtering, principal component analysis, and multiscale transforms for real-world geospatial applications. Publication analysis reveals consistent focus on operational image processing solutions between 2010-2022, with recent work emphasizing radiometric correction for analogue airborne data and real-time vignetting estimation. His output bridges theoretical image science and field-deployable techniques for national mapping agencies. He has advised two significant internships: Emeric DELAYGUE's 2009 research on aerial motion blur deconvolution and Vincent DAVAL's 2012 work on nighttime mobile imaging restoration. These projects reflect his expertise in image degradation correction within ENSG's PPMD program framework. As an active GEOVIS team member, LELÉGARD continues advancing image quality methodologies at MATIS laboratory, focusing on radiometric processing innovations for IGN's geospatial data pipelines while maintaining selective teaching engagements at ENSG.

Baptiste Lafabregueمشاهده پروفایل

دانشیار

• Machine Learning
• Time Series Analysis
• Clustering
• +۳ مورد دیگر

Baptiste Lafabregue is an Associate Professor of Computer Science at the University of Strasbourg, affiliated with Télécom Physique Strasbourg and the ICube Laboratory. His research focuses on artificial intelligence with specialization in clustering algorithms and time series analysis, particularly applied to remote sensing data. He teaches undergraduate and graduate courses in computer science while maintaining an active research program in machine learning. His educational background includes a PhD in Computer Science from Université de Haute Alsace (2021), an MSc in Computer Science Engineering from École Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise (2014), and a BSc in Computer Science from University of Strasbourg (2012). Lafabregue's research interests center around time series analysis and collaborative clustering methodologies. His work bridges theoretical machine learning with practical applications in satellite imagery and remote sensing, developing novel constrained clustering approaches that incorporate domain-specific knowledge while reducing reliance on labeled data. His research has significant implications for agricultural mapping and environmental monitoring. His publication record demonstrates a clear progression in deep learning applications for time series clustering, with increasing focus on satellite image time series analysis. The research shows evolution from traditional constrained clustering methods to deep learning integration, with particular attention to practical implementation challenges in remote sensing applications. Lafabregue has managed multiple research projects including two MSc research projects and supervised interns working on clustering and segmentation libraries for remote-sensing images. His professional experience includes research engineering positions focused on re-engineering and maintaining clustering libraries, demonstrating both theoretical and practical expertise in his field. He is a member of the Science of Data and Knowledge (SDC) team at the ICube research laboratory, where he contributes to advancing methodologies in time series analysis and clustering algorithms with applications to real-world remote sensing problems.

Julie Bourbeillonمشاهده پروفایل

مدرس

• Bioinformatics
• Systems Biology
• Artificial Intelligence
• +۹ مورد دیگر

Julie Bourbeillon is a Lecturer in Computer Science at Institut Agro Rennes-Angers , where she co-directs the Department of Statistics and Computer Science. Her work bridges Bioinformatics , Computer Vision , and Data Integration with applications in Plant Biology and Horticulture . She has developed educational frameworks for integrating digital skills into horticultural training using the PiX framework . Education : PhD in Computer Science (2007, Université Grenoble 1), Master of Science and Engineering for Health and Medicine (2004), Engineer (2002, INAPG) Her research focuses on semantic distance , heterogeneous data integration , and data visualization for biological datasets. She leads the DIVIS project for handling complex phenotypic data and co-developed ELVIS and QuaDS software tools. Key projects include: DIGITOM (2024-2027): Digital twins for climate-resilient agriculture ERICA (2025-2026): Robotic climate mapping in greenhouses GRIOTE (2014-2018): Bioinformatics collaboration

Maria Vakalopoulouمشاهده پروفایل

استاد

• Medical Imaging
• Deep Learning
• Computer Vision
• +۴ مورد دیگر

Maria Vakalopoulou leads her eponymous laboratory focused on Mathematics and Computer Science for Complexity and Systems. She directs cutting-edge research at the intersection of artificial intelligence, medical imaging, and remote sensing. Her interdisciplinary work bridges computer science fundamentals with clinical and geospatial applications. Her primary research develops novel deep learning methodologies for: Medical image analysis (CT, MRI, digital pathology) Remote sensing and satellite imagery processing Explainable AI for clinical decision support Unsupervised/self-supervised learning techniques Graph neural networks for biomedical data Publication analysis reveals strong focus on: AI-powered diagnostic systems for oncology and pulmonary diseases Advanced image segmentation and registration techniques Computational pathology for cancer prognosis Domain-adaptive learning for medical applications Physics-informed AI for radiotherapy planning Collaborates extensively with medical institutions including Gustave Roussy and Université Paris-Saclay researchers. Leads development of novel frameworks like GHOST (graph-based similarity transformations) and Hyper-AdaC (adaptive hypergraphs for pathology).

Emmanuel Cledatمشاهده پروفایل

دانشیار

• Photogrammetry
• Sensor Calibration
• Risk Measurement for Cyclists
• +۴ مورد دیگر

Emmanuel Cledat is an Associate Professor of photogrammetry at the National Institute of Geographic and Forest Information (IGN) and lecturer at the ENSG (National School of Geographic Sciences), where he teaches courses in sensor technology, mathematics for photogrammetry, and applied photogrammetry. As a member of the UMR Lastig research unit and ACTE research team, he conducts interdisciplinary work spanning photogrammetry, geomatics, and transportation safety. His research interests focus on photogrammetry , sensor calibration , and measurement of risks faced by cyclists . Dr. Cledat specializes in macro-photogrammetry of small objects, drone-based mapping systems, and GNSS-denied environment navigation. His methodological expertise includes camera calibration models, 3D reconstruction, and fusion of photogrammetric and LiDAR data. Dr. Cledat's publication record demonstrates consistent contributions to photogrammetry and geospatial sciences since 2016, with recent work exploring AI applications in geomatics and historical bridge modeling. His research shows a clear trajectory from foundational work on drone photogrammetry calibration to more applied projects addressing transportation safety and cultural heritage preservation. ISPRS Best Young Author Award 2020 As principal investigator, Dr. Cledat leads the CycloSafe project which quantifies cycling risks using LIDAR-equipped bicycles, and the EntrePonts project focused on 3D modeling of historical bridge models from the 17th-19th centuries. His teaching portfolio spans undergraduate and graduate courses in photogrammetry fundamentals, underwater photogrammetry, and climate change workshops. His laboratory work centers around the UMR Lastig research unit, with projects involving drone mapping systems, 3D TOF camera calibration, and photogrammetric fieldwork methodologies for both small objects and large-scale environmental mapping.

Elliot Vincentمشاهده پروفایل

پژوهشگر

• Machine Learning
• Computer Vision
• Remote Sensing
• +۳ مورد دیگر

Elliot Vincent is a Researcher affiliated with the French National Institute of Geographic and Forest Information (IGN) and the Université Gustave Eiffel , working in the LASTIG research unit . He holds a PhD in Computer Science from Ecole des Ponts ParisTech and Inria Paris , supervised by Mathieu Aubry and Jean Ponce. Research Interests Deep learning for geospatial 2D/3D data Change detection in satellite imagery Temporal domain shift analysis Spatial generalization frameworks Recent Publications focus on satellite time series analysis, unsupervised 3D scene parsing, and novel architectures for domain adaptation. His work includes the creation of the DAFA-LS dataset for archaeological monitoring and the OpenStreetView-5M dataset for global geolocation. Scientific Awards 2025: Best Student Paper Award at CVPR EARTHVISION Workshop 2025: Recognized as CVPR 2025 Outstanding Reviewer Grants include European Research Council (ERC) support for the DISCOVER project and resources from GENCI for HPC access. Labs & Teams include IGN , LASTIG , LIGM , and Inria Paris , with collaborations extending to NYU's Center for Data Science.

Azelle Courtialمشاهده پروفایل

پژوهشگر

• Map generalization
• Deep learning
• Multi-scale maps
• +۳ مورد دیگر

Azelle Courtial is a Researcher at Institut Géographique National (IGN) , specializing in deep learning applications for cartographic generalization within the MEIG research team (Modélisation des Environnements Inhabités et Généralisation). Her work focuses on multi-scale mapping automation and spatial data representations , with recent contributions in GAN-based mountain road generalization and deep learning benchmark development . Education: PhD in Geographic Information Sciences (Université Paris-Est, 2023), Master's in GIS (2019), Licence in Math & Informatics (2017) Projects: ERC Consolidator Grant recipient (2021-2026) Software: Developer of CartAGen4Py and DeepMapGen libraries Her publications demonstrate a research trajectory combining deep learning for map generalization multi-scale cartography principles constraint-based evaluation frameworks spatial relation modeling in GIS Scientific recognition includes: Best short paper award at AGILE Conference 2022 Teaching contributions span spatial databases , webmapping , and GIS programming , with responsibilities in course material development and student project supervision.

Florence Tupinمشاهده پروفایل

استاد

• Synthetic Aperture Radar (SAR)
• Image Processing
• Deep Learning
• +۳ مورد دیگر

Florence Tupin is a Professor at Télécom Paris (Institut Polytechnique de Paris) and head of the Image, Data, Signal department. She leads the IMAGES research team at LTCI Laboratory, focusing on advanced SAR image processing, deep learning applications in remote sensing, and 3D reconstruction for earth observation. Her work bridges theoretical models and large-scale geospatial data exploitation. Her research integrates statistical modeling , non-local filtering , and deep neural networks to address challenges in SAR despeckling, tomographic imaging, and multi-temporal analysis. She directs projects like ANR ASTRAL (2022-2025) and ALYS (2015-2021), developing open-source tools such as MuLoG and MERLIN for the remote sensing community. Publication analysis reveals dominant themes: deep learning-driven SAR restoration (45%), 3D reconstruction (25%), multi-temporal change detection (20%), and polarimetric analysis (10%). Her group consistently pioneers self-supervised methods for resource-efficient remote sensing. Awards & Recognition: IEEE Geoscience and Remote Sensing Society Distinguished Achievement (2025) Advising & Grants: Directs 9 PhD students and 4 postdocs; secured €2M+ funding (ANR, CNES, CEA). Recent PhDs focus on deep learning for SAR tomography, multi-modal fusion, and Arctic monitoring. Leads Futur & Rupture initiatives on forest biomass estimation. Labs & Teams: Heads the IMAGES team (20 researchers) at LTCI Laboratory. Collaborates with CNES, CEA, and international partners (Wuhan University, Arctic University of Norway) on satellite data exploitation.

Lionel Bombrunمشاهده پروفایل

دانشیار

• Signal Processing
• Image Processing
• Remote Sensing
• +۵ مورد دیگر

Lionel Bombrun is an Associate Professor at the University of Bordeaux, specializing in Signal and Image Processing within the MOTIVE team at IMS Bordeaux. His research focuses on the application of Riemannian geometry to texture analysis, remote sensing, and machine learning problems. His educational background includes advanced studies in signal processing and mathematics, though specific degrees aren't detailed in the provided text. His research interests span multiple domains including: Statistical modeling on Riemannian manifolds Covariance matrix analysis for texture classification Wavelet-based feature extraction Remote sensing applications for environmental monitoring Machine learning approaches for hyperspectral and radar data Bombrun's publication record shows consistent contributions to high-impact journals, particularly in IEEE Transactions. His recent work demonstrates growing interest in applying conformal prediction and deep learning techniques to aviation safety and precision agriculture. The publications reveal a strong pattern of interdisciplinary collaboration across mathematics, engineering, and environmental science domains. Among his notable scientific contributions is the development of Riemannian statistical models for covariance matrix descriptors, which has become influential in texture analysis and remote sensing classification tasks. Professor Bombrun actively collaborates with researchers across multiple institutions and industries, particularly in applications related to vineyard monitoring, forest management, and aircraft navigation systems. His work demonstrates both theoretical depth in mathematical statistics and practical applications in real-world problems.

• Statistical learning in high dimensions
• Statistical learning on networks
• Functional data analysis
• +۱۲ مورد دیگر

Charles Bouveyron is a Full Professor of Statistics at Université Côte d'Azur, Nice, France. He holds a Chair in Artificial Intelligence and serves as Director of the Institut 3IA Côte d'Azur, while also leading the Inria research team MAASAI on Statistical Learning and Artificial Intelligence. Université Côte d'Azur: Full Professor of Statistics (2019-present) Institut 3IA Côte d'Azur: Director (2019-present) Inria: MAASAI Team Leader (2019-present) His research focuses on statistical learning methodologies for high-dimensional data, network analysis, functional data modeling, and deep latent variable approaches. Key applications include medical diagnosis through radiomics, ecological monitoring, astrophysics data analysis, and humanities data science. Recent publications emphasize dynamic co-clustering techniques for count data streams, deep latent position models for network analysis, and discriminative clustering frameworks using generalized mutual information. His work integrates Bayesian sparsity, probabilistic PCA, and robust classification methods. Software development remains a core activity with tools like HDclassif, FunLBM, and Linkage.fr platform for network analysis with textual edges. He has mentored over 20 PhD/postdoc researchers in statistical learning and AI applications.

• Computer Science
• Artificial Intelligence
• Data Mining
• +۳ مورد دیگر

Cyril De Runz is an Associate Professor at the University Institute of Technology of Blois (IUT Blois), University of Tours, France, affiliated with the Department of Multimedia and Internet Professions and the Fundamental and Applied Computer Science Laboratory of Tours (LIFAT, UR 6300). He also contributes to the Polytechnic School of the University of Tours (EPU), focusing on interdisciplinary computer science applications. His research spans Artificial Intelligence, Data Mining, Wireless Sensor Networks, Geographic Information Systems, and Human-Computer Interaction. Key areas include cycling infrastructure analysis using OpenStreetMap data, automatic dashboard generation for business intelligence, employee attrition modeling through sequential pattern mining, and optimization of sensor network coverage. His work bridges theoretical computer science with practical urban planning and human resources applications. Analysis of his 2023-2025 publications reveals strong trends in edge-AI deployment (e.g., ternarized vision-language models), advanced wireless sensor network strategies, and integration of multi-source data for transportation and workforce analytics. His methodologies often combine probabilistic modeling, fuzzy logic for imperfect geographic data, and deep learning adaptations. De Runz actively participates in LIFAT laboratory research, emphasizing interdisciplinary collaboration across civil engineering, social sciences, and energy systems. His projects frequently address real-world challenges like cycling safety, urban mobility, and business intelligence automation. No verifiable information on student advising, research grants, or scientific awards was found in the provided sources.

• Multi-source Sensor Fusion
• Semantic Mapping
• Collaborative Robotics
• +۵ مورد دیگر

Hiba Al-Assaad serves as a Teacher-researcher at CESI Higher Education Group in Toulouse, France, specializing in Engineering and Digital Tools within the Computer Networks and Telecommunications domain. Her work bridges academic instruction in preparatory and engineering cycles with advanced research in robotics and navigation systems. Her research focuses on multi-source sensor fusion, semantic mapping for mobile robotics, and cyber-physical systems. Key areas include developing robust navigation algorithms using digital elevation models, creating decentralized decision systems for industrial applications, and advancing federated learning frameworks. Her work consistently addresses real-world industrial challenges through collaborative robotics and smart transportation solutions. Analysis of her recent publications reveals a strong trajectory toward industrial cyber-physical systems, with increasing emphasis on federated learning, meta-algorithms, and human-robot collaboration in manufacturing environments. Her research integrates geospatial engineering with machine learning to solve navigation and perception challenges. She actively supervises doctoral candidates including A. Achour (defense 2024) researching real-time semantic mapping with robot swarms, and B. Guendouzi (defense 2025) developing decision support systems for industrial cyber-physical environments. Her technical contributions span from fundamental navigation algorithms to cutting-edge machine learning applications, maintaining consistent output across journals like International Journal of Image and Data Fusion , IEEE CSR , and Journal of Network and Computer Applications .

Romain Vergneمشاهده پروفایل

دانشیار

• Computer Graphics
• Visual Perception
• Shape Depiction
• +۵ مورد دیگر

Romain Vergne is an Associate Professor at the University of Grenoble Alpes, France, and a researcher affiliated with the Maverick team (Inria, LJK) since 2012. Previously, he conducted postdoctoral research at Justus Liebig University Giessen (Germany). His research focuses on the phenomenological links between shapes, light, and material perception, aiming to develop perceptually plausible computer graphics tools. Key interests include shape depiction, visual perception, texture synthesis, and appearance control via his GPU-centric node-based system Gratin for 2D/3D data manipulation. Best Paper Awards: AFIG 2018, Expressive 2018, AFIG 2015 Honorable Mentions: NPAR 2011, I3D 2010 Recent publications explore Gabor noise optimization, motion-coherent stylization, and non-photorealistic rendering frameworks. He also contributes to eco-feedback visualization systems and cartographic style extensions.

• Intelligent Transport Systems
• Artificial Intelligence
• Multi-Sensor Fusion
• +۵ مورد دیگر

AL ASSAAD Hiba is a Researcher-Lecturer at CESI (Centre d’Études et de Sécurité Informatique), based at the Toulouse Campus. She holds a PhD from the University of Littorale Côte d’Opale (2020) titled « Contribution of digital elevation models for the enrichment of navigation maps by multi-sensor fusion » , and an engineering degree in Computer Science and Telecommunications from University Antonine – Lebanon (2016). Her work focuses on Intelligent Transport Systems, Artificial Intelligence, and multi-sensor fusion techniques. Her research interests include advanced navigation systems leveraging GPS/INS/DEM integration, particulate and Kalman filtering methods, and the application of statistical modeling in geospatial data. Recent work extends into semantic mapping for robotics and federated learning in industrial cyber-physical systems. Publications highlight contributions to vehicle attitude estimation via particle filtering, GNSS-based navigation enhancements using DEM data, and fall prediction algorithms. Her research bridges theoretical advancements in sensor fusion with practical applications in autonomous systems and industrial automation. No scientific awards are explicitly noted in the provided materials. Advising activities and grant details remain unspecified. She is affiliated with CESI’s Engineering and Numerical Tools research team, contributing to educational activities in computer sciences at engineering curriculum levels 3 and 4.

Jonathan Weberمشاهده پروفایل

استاد

• Time Series Classification
• Deep Learning
• Computer Vision
• +۲ مورد دیگر

Jonathan Weber is Full Professor in Computer Science at Université de Haute-Alsace and Head of the Computer Science and Network Department at ENSISA. His research develops deep learning methods for time series analysis, image processing, and computer vision applications. Research focuses on time series classification, clustering, and generation using deep neural networks. Applications span medical imaging, remote sensing, rehabilitation assessment, and geospatial mapping. Recent publications establish evaluation frameworks for human motion generation, develop efficient architectures for time series classification, and create neural approaches for hiking map generation. His team created the InceptionTime model for time series classification. Professor Weber leads the MSD (Modeling of Dynamic Systems) research team at IRIMAS and has supervised multiple PhD students in computer vision and time series analysis.