Object-Level Semantic Map Construction for Dynamic Scenes
Visual simultaneous localization and mapping (SLAM) is challenging in dynamic environments as moving objects can impair camera pose tracking and mapping. This paper introduces a method for robust dense bject-level SLAM in dynamic environments that takes a live stream of RGB-D frame data as input, de...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/2/645 |
| _version_ | 1797413262520745984 |
|---|---|
| author | Xujie Kang Jing Li Xiangtao Fan Hongdeng Jian Chen Xu |
| author_facet | Xujie Kang Jing Li Xiangtao Fan Hongdeng Jian Chen Xu |
| author_sort | Xujie Kang |
| collection | DOAJ |
| description | Visual simultaneous localization and mapping (SLAM) is challenging in dynamic environments as moving objects can impair camera pose tracking and mapping. This paper introduces a method for robust dense bject-level SLAM in dynamic environments that takes a live stream of RGB-D frame data as input, detects moving objects, and segments the scene into different objects while simultaneously tracking and reconstructing their 3D structures. This approach provides a new method of dynamic object detection, which integrates prior knowledge of the object model database constructed, object-oriented 3D tracking against the camera pose, and the association between the instance segmentation results on the current frame data and an object database to find dynamic objects in the current frame. By leveraging the 3D static model for frame-to-model alignment, as well as dynamic object culling, the camera motion estimation reduced the overall drift. According to the camera pose accuracy and instance segmentation results, an object-level semantic map representation was constructed for the world map. The experimental results obtained using the TUM RGB-D dataset, which compares the proposed method to the related state-of-the-art approaches, demonstrating that our method achieves similar performance in static scenes and improved accuracy and robustness in dynamic scenes. |
| first_indexed | 2024-03-09T05:15:19Z |
| format | Article |
| id | doaj.art-c36ceae1473641d8a643d9d49aec0606 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T05:15:19Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c36ceae1473641d8a643d9d49aec06062023-12-03T12:46:38ZengMDPI AGApplied Sciences2076-34172021-01-0111264510.3390/app11020645Object-Level Semantic Map Construction for Dynamic ScenesXujie Kang0Jing Li1Xiangtao Fan2Hongdeng Jian3Chen Xu4Key Laboratory of Digital Earth Science, Aerospace Information Research Institute (AIR), Chinese Academy of Sciences, Beijing 100094, ChinaNational Engineering Research Center for Geoinformatics, Aerospace Information Research Institute (AIR), Chinese Academy of Sciences, No. 20A, Datun Road, Chaoyang District, Beijing 100101, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute (AIR), Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute (AIR), Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute (AIR), Chinese Academy of Sciences, Beijing 100094, ChinaVisual simultaneous localization and mapping (SLAM) is challenging in dynamic environments as moving objects can impair camera pose tracking and mapping. This paper introduces a method for robust dense bject-level SLAM in dynamic environments that takes a live stream of RGB-D frame data as input, detects moving objects, and segments the scene into different objects while simultaneously tracking and reconstructing their 3D structures. This approach provides a new method of dynamic object detection, which integrates prior knowledge of the object model database constructed, object-oriented 3D tracking against the camera pose, and the association between the instance segmentation results on the current frame data and an object database to find dynamic objects in the current frame. By leveraging the 3D static model for frame-to-model alignment, as well as dynamic object culling, the camera motion estimation reduced the overall drift. According to the camera pose accuracy and instance segmentation results, an object-level semantic map representation was constructed for the world map. The experimental results obtained using the TUM RGB-D dataset, which compares the proposed method to the related state-of-the-art approaches, demonstrating that our method achieves similar performance in static scenes and improved accuracy and robustness in dynamic scenes.https://www.mdpi.com/2076-3417/11/2/645object trackinginstance segmentationdynamic simultaneous localization and mappingcamera pose tracking |
| spellingShingle | Xujie Kang Jing Li Xiangtao Fan Hongdeng Jian Chen Xu Object-Level Semantic Map Construction for Dynamic Scenes Applied Sciences object tracking instance segmentation dynamic simultaneous localization and mapping camera pose tracking |
| title | Object-Level Semantic Map Construction for Dynamic Scenes |
| title_full | Object-Level Semantic Map Construction for Dynamic Scenes |
| title_fullStr | Object-Level Semantic Map Construction for Dynamic Scenes |
| title_full_unstemmed | Object-Level Semantic Map Construction for Dynamic Scenes |
| title_short | Object-Level Semantic Map Construction for Dynamic Scenes |
| title_sort | object level semantic map construction for dynamic scenes |
| topic | object tracking instance segmentation dynamic simultaneous localization and mapping camera pose tracking |
| url | https://www.mdpi.com/2076-3417/11/2/645 |
| work_keys_str_mv | AT xujiekang objectlevelsemanticmapconstructionfordynamicscenes AT jingli objectlevelsemanticmapconstructionfordynamicscenes AT xiangtaofan objectlevelsemanticmapconstructionfordynamicscenes AT hongdengjian objectlevelsemanticmapconstructionfordynamicscenes AT chenxu objectlevelsemanticmapconstructionfordynamicscenes |