Visual SLAM and structure from motion in dynamic environments
In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization and Mapping (visual SLAM) techniques have gained significant interest from both the computer vision and robotic communities. Many variants of these techniques have started to make an impact in a wide range of a...
| Հիմնական հեղինակներ: | , , |
|---|---|
| Ձևաչափ: | Journal article |
| Լեզու: | English |
| Հրապարակվել է: |
Association for Computing Machinery
2018
|
| _version_ | 1826260191532810240 |
|---|---|
| author | Saputra, M Markham, A Trigoni, N |
| author_facet | Saputra, M Markham, A Trigoni, N |
| author_sort | Saputra, M |
| collection | OXFORD |
| description | In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization and Mapping (visual SLAM) techniques have gained significant interest from both the computer vision and robotic communities. Many variants of these techniques have started to make an impact in a wide range of applications, including robot navigation and augmented reality. However, despite some remarkable results in these areas, most SfM and visual SLAM techniques operate based on the assumption that the observed environment is static. However, when faced with moving objects, overall system accuracy can be jeopardized. In this article, we present for the first time a survey of visual SLAM and SfM techniques that are targeted toward operation in dynamic environments. We identify three main problems: how to perform reconstruction (robust visual SLAM), how to segment and track dynamic objects, and how to achieve joint motion segmentation and reconstruction. Based on this categorization, we provide a comprehensive taxonomy of existing approaches. Finally, the advantages and disadvantages of each solution class are critically discussed from the perspective of practicality and robustness. |
| first_indexed | 2024-03-06T19:01:44Z |
| format | Journal article |
| id | oxford-uuid:13c4132e-6a15-4b36-8a85-8cb62b98f42e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T19:01:44Z |
| publishDate | 2018 |
| publisher | Association for Computing Machinery |
| record_format | dspace |
| spelling | oxford-uuid:13c4132e-6a15-4b36-8a85-8cb62b98f42e2022-03-26T10:15:46ZVisual SLAM and structure from motion in dynamic environmentsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:13c4132e-6a15-4b36-8a85-8cb62b98f42eEnglishSymplectic Elements at OxfordAssociation for Computing Machinery2018Saputra, MMarkham, ATrigoni, NIn the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization and Mapping (visual SLAM) techniques have gained significant interest from both the computer vision and robotic communities. Many variants of these techniques have started to make an impact in a wide range of applications, including robot navigation and augmented reality. However, despite some remarkable results in these areas, most SfM and visual SLAM techniques operate based on the assumption that the observed environment is static. However, when faced with moving objects, overall system accuracy can be jeopardized. In this article, we present for the first time a survey of visual SLAM and SfM techniques that are targeted toward operation in dynamic environments. We identify three main problems: how to perform reconstruction (robust visual SLAM), how to segment and track dynamic objects, and how to achieve joint motion segmentation and reconstruction. Based on this categorization, we provide a comprehensive taxonomy of existing approaches. Finally, the advantages and disadvantages of each solution class are critically discussed from the perspective of practicality and robustness. |
| spellingShingle | Saputra, M Markham, A Trigoni, N Visual SLAM and structure from motion in dynamic environments |
| title | Visual SLAM and structure from motion in dynamic environments |
| title_full | Visual SLAM and structure from motion in dynamic environments |
| title_fullStr | Visual SLAM and structure from motion in dynamic environments |
| title_full_unstemmed | Visual SLAM and structure from motion in dynamic environments |
| title_short | Visual SLAM and structure from motion in dynamic environments |
| title_sort | visual slam and structure from motion in dynamic environments |
| work_keys_str_mv | AT saputram visualslamandstructurefrommotionindynamicenvironments AT markhama visualslamandstructurefrommotionindynamicenvironments AT trigonin visualslamandstructurefrommotionindynamicenvironments |