Accurate and Robust Monocular SLAM with Omnidirectional Cameras
Simultaneous localization and mapping (SLAM) are fundamental elements for many emerging technologies, such as autonomous driving and augmented reality. For this paper, to get more information, we developed an improved monocular visual SLAM system by using omnidirectional cameras. Our method extends...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/20/4494 |
| _version_ | 1811305793057718272 |
|---|---|
| author | Shuoyuan Liu Peng Guo Lihui Feng Aiying Yang |
| author_facet | Shuoyuan Liu Peng Guo Lihui Feng Aiying Yang |
| author_sort | Shuoyuan Liu |
| collection | DOAJ |
| description | Simultaneous localization and mapping (SLAM) are fundamental elements for many emerging technologies, such as autonomous driving and augmented reality. For this paper, to get more information, we developed an improved monocular visual SLAM system by using omnidirectional cameras. Our method extends the ORB-SLAM framework with the enhanced unified camera model as a projection function, which can be applied to catadioptric systems and wide-angle fisheye cameras with 195 degrees field-of-view. The proposed system can use the full area of the images even with strong distortion. For omnidirectional cameras, a map initialization method is proposed. We analytically derive the Jacobian matrices of the reprojection errors with respect to the camera pose and 3D position of points. The proposed SLAM has been extensively tested in real-world datasets. The results show positioning error is less than 0.1% in a small indoor environment and is less than 1.5% in a large environment. The results demonstrate that our method is real-time, and increases its accuracy and robustness over the normal systems based on the pinhole model. |
| first_indexed | 2024-04-13T08:32:43Z |
| format | Article |
| id | doaj.art-d01f005a4dc44f9ea6549630ad67e586 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T08:32:43Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d01f005a4dc44f9ea6549630ad67e5862022-12-22T02:54:13ZengMDPI AGSensors1424-82202019-10-011920449410.3390/s19204494s19204494Accurate and Robust Monocular SLAM with Omnidirectional CamerasShuoyuan Liu0Peng Guo1Lihui Feng2Aiying Yang3The Key Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100086, ChinaThe Key Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100086, ChinaThe Key Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100086, ChinaThe Key Laboratory of Photonics Information Technology, Ministry of Industry and Information Technology, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100086, ChinaSimultaneous localization and mapping (SLAM) are fundamental elements for many emerging technologies, such as autonomous driving and augmented reality. For this paper, to get more information, we developed an improved monocular visual SLAM system by using omnidirectional cameras. Our method extends the ORB-SLAM framework with the enhanced unified camera model as a projection function, which can be applied to catadioptric systems and wide-angle fisheye cameras with 195 degrees field-of-view. The proposed system can use the full area of the images even with strong distortion. For omnidirectional cameras, a map initialization method is proposed. We analytically derive the Jacobian matrices of the reprojection errors with respect to the camera pose and 3D position of points. The proposed SLAM has been extensively tested in real-world datasets. The results show positioning error is less than 0.1% in a small indoor environment and is less than 1.5% in a large environment. The results demonstrate that our method is real-time, and increases its accuracy and robustness over the normal systems based on the pinhole model.https://www.mdpi.com/1424-8220/19/20/4494simultaneous localization and mappingvisual slammap initializationfisheye camerasomnidirectional cameras |
| spellingShingle | Shuoyuan Liu Peng Guo Lihui Feng Aiying Yang Accurate and Robust Monocular SLAM with Omnidirectional Cameras Sensors simultaneous localization and mapping visual slam map initialization fisheye cameras omnidirectional cameras |
| title | Accurate and Robust Monocular SLAM with Omnidirectional Cameras |
| title_full | Accurate and Robust Monocular SLAM with Omnidirectional Cameras |
| title_fullStr | Accurate and Robust Monocular SLAM with Omnidirectional Cameras |
| title_full_unstemmed | Accurate and Robust Monocular SLAM with Omnidirectional Cameras |
| title_short | Accurate and Robust Monocular SLAM with Omnidirectional Cameras |
| title_sort | accurate and robust monocular slam with omnidirectional cameras |
| topic | simultaneous localization and mapping visual slam map initialization fisheye cameras omnidirectional cameras |
| url | https://www.mdpi.com/1424-8220/19/20/4494 |
| work_keys_str_mv | AT shuoyuanliu accurateandrobustmonocularslamwithomnidirectionalcameras AT pengguo accurateandrobustmonocularslamwithomnidirectionalcameras AT lihuifeng accurateandrobustmonocularslamwithomnidirectionalcameras AT aiyingyang accurateandrobustmonocularslamwithomnidirectionalcameras |