Abstract
This paper presents an enhanced indoor RGB-D simultaneously localisation and mapping (SLAM) system based on the integration of plane and point features. A new method was proposed to register each point feature to a corresponding plane feature and then modify its position accordingly. The plane features are parallelly extracted from depth data sources and used jointly to solve the camera pose with point features. Plane features are stored on the map as the same as point features. Both point and plane features are used for backend optimisation, where the weights associated with features can be dynamically updated. At the same time, the on-plane feature points are fixed during the optimisation. The proposed method has been tested with open-source benchmarks, including the scenarios with or without a structured environment. Experiment results demonstrated that the proposed algorithm performs better than other widely cited visual SLAM systems in some structured environments.
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE 12th International Conference Indoor Positioning and Indoor Navigation |
Publisher | IEEE |
Number of pages | 8 |
ISBN (Electronic) | 978-1-7281-6218-8 |
ISBN (Print) | 978-1-7281-6219-5 |
Publication status | Published (in print/issue) - 26 Oct 2022 |
Event | Twelfth International Conference on Indoor Positioning and Indoor Navigation - Beijing, China Duration: 5 Sept 2022 → 7 Sept 2022 Conference number: 12 http://www.ipin-conference.org/2022/index.html |
Publication series
Name | |
---|---|
ISSN (Print) | 2162-7347 |
ISSN (Electronic) | 2471-917X |
Conference
Conference | Twelfth International Conference on Indoor Positioning and Indoor Navigation |
---|---|
Abbreviated title | IPIN 2022 |
Country/Territory | China |
City | Beijing |
Period | 5/09/22 → 7/09/22 |
Internet address |
Keywords
- SLAM
- Visual SLAM
- Geometry Information
- Plane Feature