Deep Learning Techniques for Visual SLAM: A Survey
Visual Simultaneous Localization and Mapping (VSLAM) has attracted considerable attention in recent years. This task involves using visual sensors to localize a robot while simultaneously constructing an internal representation of its environment. Traditional VSLAM methods involve the laborious hand...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10054007/ |
| _version_ | 1827999946019700736 |
|---|---|
| author | Saad Mokssit Daniel Bonilla Licea Bassma Guermah Mounir Ghogho |
| author_facet | Saad Mokssit Daniel Bonilla Licea Bassma Guermah Mounir Ghogho |
| author_sort | Saad Mokssit |
| collection | DOAJ |
| description | Visual Simultaneous Localization and Mapping (VSLAM) has attracted considerable attention in recent years. This task involves using visual sensors to localize a robot while simultaneously constructing an internal representation of its environment. Traditional VSLAM methods involve the laborious hand-crafted design of visual features and complex geometric models. As a result, they are generally limited to simple environments with easily identifiable textures. Recent years, however, have witnessed the development of deep learning techniques for VSLAM. This is primarily due to their capability of modeling complex features of the environment in a completely data-driven manner. In this paper, we present a survey of relevant deep learning-based VSLAM methods and suggest a new taxonomy for the subject. We also discuss some of the current challenges and possible directions for this field of study. |
| first_indexed | 2024-04-10T06:06:25Z |
| format | Article |
| id | doaj.art-a1a324b126d242ed943554882ce7134a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:06:25Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a1a324b126d242ed943554882ce7134a2023-03-03T00:01:15ZengIEEEIEEE Access2169-35362023-01-0111200262005010.1109/ACCESS.2023.324966110054007Deep Learning Techniques for Visual SLAM: A SurveySaad Mokssit0https://orcid.org/0000-0002-2262-918XDaniel Bonilla Licea1Bassma Guermah2Mounir Ghogho3https://orcid.org/0000-0002-0055-7867TICLab, College of Engineering and Architecture, International University of Rabat, Rabat, MoroccoMulti-Robot Systems Group (MRS), Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech RepublicTICLab, College of Engineering and Architecture, International University of Rabat, Rabat, MoroccoTICLab, College of Engineering and Architecture, International University of Rabat, Rabat, MoroccoVisual Simultaneous Localization and Mapping (VSLAM) has attracted considerable attention in recent years. This task involves using visual sensors to localize a robot while simultaneously constructing an internal representation of its environment. Traditional VSLAM methods involve the laborious hand-crafted design of visual features and complex geometric models. As a result, they are generally limited to simple environments with easily identifiable textures. Recent years, however, have witnessed the development of deep learning techniques for VSLAM. This is primarily due to their capability of modeling complex features of the environment in a completely data-driven manner. In this paper, we present a survey of relevant deep learning-based VSLAM methods and suggest a new taxonomy for the subject. We also discuss some of the current challenges and possible directions for this field of study.https://ieeexplore.ieee.org/document/10054007/Visual SLAMdeep learningjoint learningactive learningsurvey |
| spellingShingle | Saad Mokssit Daniel Bonilla Licea Bassma Guermah Mounir Ghogho Deep Learning Techniques for Visual SLAM: A Survey IEEE Access Visual SLAM deep learning joint learning active learning survey |
| title | Deep Learning Techniques for Visual SLAM: A Survey |
| title_full | Deep Learning Techniques for Visual SLAM: A Survey |
| title_fullStr | Deep Learning Techniques for Visual SLAM: A Survey |
| title_full_unstemmed | Deep Learning Techniques for Visual SLAM: A Survey |
| title_short | Deep Learning Techniques for Visual SLAM: A Survey |
| title_sort | deep learning techniques for visual slam a survey |
| topic | Visual SLAM deep learning joint learning active learning survey |
| url | https://ieeexplore.ieee.org/document/10054007/ |
| work_keys_str_mv | AT saadmokssit deeplearningtechniquesforvisualslamasurvey AT danielbonillalicea deeplearningtechniquesforvisualslamasurvey AT bassmaguermah deeplearningtechniquesforvisualslamasurvey AT mounirghogho deeplearningtechniquesforvisualslamasurvey |