Please use this identifier to cite or link to this item: http://dspace.ensta.edu.dz/jspui/handle/123456789/566
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLAHOUAL, Yassine-
dc.contributor.authorRebai, karima (Directeur de thèse)-
dc.date.accessioned2026-11-10T10:09:13Z-
dc.date.available2026-11-10T10:09:13Z-
dc.date.issued2022-
dc.identifier.urihttp://dspace.ensta.edu.dz/jspui/handle/123456789/566-
dc.descriptionMémoire de fin d’étude de Master : Automatique et Informatique Industrielle: Alger, Ecole Nationale Supérieure des Technologie Avancées (ex ENST): 2022en_US
dc.description.abstractThe ability of autonomous vehicles to navigate in challenging maps with continuously changing conditions is so impressive and still improving. A key component that enables these intelligent vehicles to overcome such conditions and become more autonomous is the precision of the perception and localization systems. As part of the localization system, place recognition has benefited from recent developments, especially with the emergence of deep learning frameworks. This article studies the current state-of-the-art approaches and methods used in place recognition based on deep learning. Firstly, introduces the full picture of place recognition concepts. Then, addresses its challenges. Finally, how deep learning can help solving those problems. The DL-based place recognition can be categorized into supervised, unsupervised, semi-supervised categories. Therefore, this article will dive into each category including the advantages and disadvantages of each in place recognition, without forgetting to mention some of the related works.en_US
dc.language.isoenen_US
dc.publisherENSTen_US
dc.subjectAutonomous Vehiclesen_US
dc.subjectPlace Recognitionen_US
dc.subjectDeep Learningen_US
dc.titlePlace Recognition for Mobile Robotsen_US
dc.typeThesisen_US
Appears in Collections:MFE- Automatique et Informatique Industrielle

Files in This Item:
File Description SizeFormat 
MASTER-LAHOUAL Yassine.pdfMémoire de Master794.5 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.