A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes
Dynamic objects bring about a large number of error accumulations in pose estimation of mobile robots in dynamic scenes, and result in the failure to build a map that is consistent with the surrounding environment. Along these lines, this paper presents a robust semi-direct 3D simultaneous localizat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/8/4/371 |
| _version_ | 1827730213920833536 |
|---|---|
| author | Bo Hu Jingwen Luo |
| author_facet | Bo Hu Jingwen Luo |
| author_sort | Bo Hu |
| collection | DOAJ |
| description | Dynamic objects bring about a large number of error accumulations in pose estimation of mobile robots in dynamic scenes, and result in the failure to build a map that is consistent with the surrounding environment. Along these lines, this paper presents a robust semi-direct 3D simultaneous localization and mapping (SLAM) algorithm for mobile robots based on dense optical flow. First, a preliminary estimation of the robot’s pose is conducted using the sparse direct method and the homography matrix is utilized to compensate for the current frame image to reduce the image deformation caused by rotation during the robot’s motion. Then, by calculating the dense optical flow field of two adjacent frames and segmenting the dynamic region in the scene based on the dynamic threshold, the local map points projected within the dynamic regions are eliminated. On this basis, the robot’s pose is optimized by minimizing the reprojection error. Moreover, a high-performance keyframe selection strategy is developed, and keyframes are inserted when the robot’s pose is successfully tracked. Meanwhile, feature points are extracted and matched to the keyframes for subsequent optimization and mapping. Considering that the direct method is subject to tracking failure in practical application scenarios, the feature points and map points of keyframes are employed in robot relocation. Finally, all keyframes and map points are used as optimization variables for global bundle adjustment (BA) optimization, so as to construct a globally consistent 3D dense octree map. A series of simulations and experiments demonstrate the superior performance of the proposed algorithm. |
| first_indexed | 2024-03-11T00:05:04Z |
| format | Article |
| id | doaj.art-097ab0c95cc54bb7b3a17b1afbb51d4d |
| institution | Directory Open Access Journal |
| issn | 2313-7673 |
| language | English |
| last_indexed | 2024-03-11T00:05:04Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj.art-097ab0c95cc54bb7b3a17b1afbb51d4d2023-11-19T00:22:56ZengMDPI AGBiomimetics2313-76732023-08-018437110.3390/biomimetics8040371A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic ScenesBo Hu0Jingwen Luo1School of Information Science and Technology, Yunnan Normal University, No. 768 Juxian Street, Chenggong District, Kunming 650500, ChinaSchool of Information Science and Technology, Yunnan Normal University, No. 768 Juxian Street, Chenggong District, Kunming 650500, ChinaDynamic objects bring about a large number of error accumulations in pose estimation of mobile robots in dynamic scenes, and result in the failure to build a map that is consistent with the surrounding environment. Along these lines, this paper presents a robust semi-direct 3D simultaneous localization and mapping (SLAM) algorithm for mobile robots based on dense optical flow. First, a preliminary estimation of the robot’s pose is conducted using the sparse direct method and the homography matrix is utilized to compensate for the current frame image to reduce the image deformation caused by rotation during the robot’s motion. Then, by calculating the dense optical flow field of two adjacent frames and segmenting the dynamic region in the scene based on the dynamic threshold, the local map points projected within the dynamic regions are eliminated. On this basis, the robot’s pose is optimized by minimizing the reprojection error. Moreover, a high-performance keyframe selection strategy is developed, and keyframes are inserted when the robot’s pose is successfully tracked. Meanwhile, feature points are extracted and matched to the keyframes for subsequent optimization and mapping. Considering that the direct method is subject to tracking failure in practical application scenarios, the feature points and map points of keyframes are employed in robot relocation. Finally, all keyframes and map points are used as optimization variables for global bundle adjustment (BA) optimization, so as to construct a globally consistent 3D dense octree map. A series of simulations and experiments demonstrate the superior performance of the proposed algorithm.https://www.mdpi.com/2313-7673/8/4/371dynamic scenesmobile robotsimultaneous localization and mapping (SLAM)semi-direct methoddense optical flowrelocation |
| spellingShingle | Bo Hu Jingwen Luo A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes Biomimetics dynamic scenes mobile robot simultaneous localization and mapping (SLAM) semi-direct method dense optical flow relocation |
| title | A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes |
| title_full | A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes |
| title_fullStr | A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes |
| title_full_unstemmed | A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes |
| title_short | A Robust Semi-Direct 3D SLAM for Mobile Robot Based on Dense Optical Flow in Dynamic Scenes |
| title_sort | robust semi direct 3d slam for mobile robot based on dense optical flow in dynamic scenes |
| topic | dynamic scenes mobile robot simultaneous localization and mapping (SLAM) semi-direct method dense optical flow relocation |
| url | https://www.mdpi.com/2313-7673/8/4/371 |
| work_keys_str_mv | AT bohu arobustsemidirect3dslamformobilerobotbasedondenseopticalflowindynamicscenes AT jingwenluo arobustsemidirect3dslamformobilerobotbasedondenseopticalflowindynamicscenes AT bohu robustsemidirect3dslamformobilerobotbasedondenseopticalflowindynamicscenes AT jingwenluo robustsemidirect3dslamformobilerobotbasedondenseopticalflowindynamicscenes |