Simultaneous Localisation and Mapping Using a Single Camera
<p>This thesis describes a system which is able to track the pose of a hand-held camera as it moves around a scene. The system builds a 3D map of point landmarks in the world while tracking the pose of the camera relative to this map using a process called simultaneous localisation and mapping...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2009
|
| Subjects: |
| _version_ | 1817932603409301504 |
|---|---|
| author | Williams, B Brian Williams |
| author2 | Reid, I |
| author_facet | Reid, I Williams, B Brian Williams |
| author_sort | Williams, B |
| collection | OXFORD |
| description | <p>This thesis describes a system which is able to track the pose of a hand-held camera as it moves around a scene. The system builds a 3D map of point landmarks in the world while tracking the pose of the camera relative to this map using a process called simultaneous localisation and mapping (SLAM). To achieve real-time performance, the map must be kept sparse, but rather than observing only the mapped landmarks like previous systems, observations are made of features across the entire image. Their deviation from the predicted epipolar geometry is used to further constrain the estimated inter-frame motion and so improves the overall accuracy. The consistency of the estimation is also improved by performing the estimation in a camera-centred coordinate frame.</p> <p>As with any such system, tracking failure is inevitable due to occlusion or sudden motion of the camera. A relocalisation module is presented which monitors the SLAM system, detects tracking failure, and then resumes tracking as soon as the conditions have improved. This relocalisation process is achieved using a new landmark recognition algorithm which is trained on-line and provides high recall and a fast recognition time.</p> <p>The relocalisation module can also be used to achieve place recognition for a loop closure detection system. By taking into account both the geometry and appearance information when determining a loop closure this module is able to outperform previous loop closure detection techniques used in monocular SLAM. After recognising an overlap, the map is then corrected using a novel trajectory alignment technique that is able to cope with the inherent scale ambiguity in monocular SLAM.</p> <p>By incorporating all of these new techniques, the system presented can perform as a robust augmented reality system, or act as a navigation tool which could be used on a mobile robot in indoor and outdoor environments.</p> |
| first_indexed | 2024-03-06T20:27:14Z |
| format | Thesis |
| id | oxford-uuid:2fccd8f6-170d-4c5b-b77b-7e371cad4df6 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:40:32Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | oxford-uuid:2fccd8f6-170d-4c5b-b77b-7e371cad4df62024-12-07T11:28:33ZSimultaneous Localisation and Mapping Using a Single CameraThesishttp://purl.org/coar/resource_type/c_db06uuid:2fccd8f6-170d-4c5b-b77b-7e371cad4df6Image understandingInformation engineeringRoboticsEnglishOxford University Research Archive - Valet2009Williams, BBrian WilliamsReid, I<p>This thesis describes a system which is able to track the pose of a hand-held camera as it moves around a scene. The system builds a 3D map of point landmarks in the world while tracking the pose of the camera relative to this map using a process called simultaneous localisation and mapping (SLAM). To achieve real-time performance, the map must be kept sparse, but rather than observing only the mapped landmarks like previous systems, observations are made of features across the entire image. Their deviation from the predicted epipolar geometry is used to further constrain the estimated inter-frame motion and so improves the overall accuracy. The consistency of the estimation is also improved by performing the estimation in a camera-centred coordinate frame.</p> <p>As with any such system, tracking failure is inevitable due to occlusion or sudden motion of the camera. A relocalisation module is presented which monitors the SLAM system, detects tracking failure, and then resumes tracking as soon as the conditions have improved. This relocalisation process is achieved using a new landmark recognition algorithm which is trained on-line and provides high recall and a fast recognition time.</p> <p>The relocalisation module can also be used to achieve place recognition for a loop closure detection system. By taking into account both the geometry and appearance information when determining a loop closure this module is able to outperform previous loop closure detection techniques used in monocular SLAM. After recognising an overlap, the map is then corrected using a novel trajectory alignment technique that is able to cope with the inherent scale ambiguity in monocular SLAM.</p> <p>By incorporating all of these new techniques, the system presented can perform as a robust augmented reality system, or act as a navigation tool which could be used on a mobile robot in indoor and outdoor environments.</p> |
| spellingShingle | Image understanding Information engineering Robotics Williams, B Brian Williams Simultaneous Localisation and Mapping Using a Single Camera |
| title | Simultaneous Localisation and Mapping Using a Single Camera |
| title_full | Simultaneous Localisation and Mapping Using a Single Camera |
| title_fullStr | Simultaneous Localisation and Mapping Using a Single Camera |
| title_full_unstemmed | Simultaneous Localisation and Mapping Using a Single Camera |
| title_short | Simultaneous Localisation and Mapping Using a Single Camera |
| title_sort | simultaneous localisation and mapping using a single camera |
| topic | Image understanding Information engineering Robotics |
| work_keys_str_mv | AT williamsb simultaneouslocalisationandmappingusingasinglecamera AT brianwilliams simultaneouslocalisationandmappingusingasinglecamera |