Hybrid SLAM and object recognition on an embedded platform
Simultaneous Localization and Mapping (SLAM) is a key localisation technique for systems such as autonomous agents. Visual SLAM is a subset of SLAM which analyzes visual information captured by cameras using visual SLAM algorithms, enabling the estimation of the camera's position and orie...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171979 |
| _version_ | 1824454551971823616 |
|---|---|
| author | Low, Timothy Zhi Hao |
| author2 | Lam Siew Kei |
| author_facet | Lam Siew Kei Low, Timothy Zhi Hao |
| author_sort | Low, Timothy Zhi Hao |
| collection | NTU |
| description | Simultaneous Localization and Mapping (SLAM) is a key localisation technique for systems
such as autonomous agents. Visual SLAM is a subset of SLAM which analyzes visual
information captured by cameras using visual SLAM algorithms, enabling the estimation of
the camera's position and orientation while simultaneously constructing a map of the
environment.
Conventional visual SLAM mainly uses sparse point clouds which fails to capture a
comprehensive representation of the environment. Thus, the maps created lacks semantic
information of the environment which causes limitations in scene understanding.
Autonomous agents that utilize visual SLAM are also commonly implemented on embedded
systems. As such, the objective of this project is to implement a hybrid SLAM system on an
embedded platform which incorporates conventional SLAM algorithms with semantic
segmentation to construct semantic dense maps.
The hybrid SLAM system is implemented and tested on the NVIDIA Jetson Xavier NX
embedded system together with the ZED2 Stereo camera for input. ORB SLAM3, a well established visual SLAM algorithm was chosen for estimating the camera poses and
orientation. The SCALE semantic segmentation is used to perform semantic segmentation
on the input provided by the ZED 2 camera. Kimera semantics is then used for processing
the camera poses, semantic and depth images to generate a semantic dense map. |
| first_indexed | 2025-02-19T03:24:07Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/171979 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:24:07Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1719792023-11-24T15:38:04Z Hybrid SLAM and object recognition on an embedded platform Low, Timothy Zhi Hao Lam Siew Kei School of Computer Science and Engineering ASSKLam@ntu.edu.sg Engineering::Computer science and engineering Simultaneous Localization and Mapping (SLAM) is a key localisation technique for systems such as autonomous agents. Visual SLAM is a subset of SLAM which analyzes visual information captured by cameras using visual SLAM algorithms, enabling the estimation of the camera's position and orientation while simultaneously constructing a map of the environment. Conventional visual SLAM mainly uses sparse point clouds which fails to capture a comprehensive representation of the environment. Thus, the maps created lacks semantic information of the environment which causes limitations in scene understanding. Autonomous agents that utilize visual SLAM are also commonly implemented on embedded systems. As such, the objective of this project is to implement a hybrid SLAM system on an embedded platform which incorporates conventional SLAM algorithms with semantic segmentation to construct semantic dense maps. The hybrid SLAM system is implemented and tested on the NVIDIA Jetson Xavier NX embedded system together with the ZED2 Stereo camera for input. ORB SLAM3, a well established visual SLAM algorithm was chosen for estimating the camera poses and orientation. The SCALE semantic segmentation is used to perform semantic segmentation on the input provided by the ZED 2 camera. Kimera semantics is then used for processing the camera poses, semantic and depth images to generate a semantic dense map. Bachelor of Engineering (Computer Science) 2023-11-20T02:54:14Z 2023-11-20T02:54:14Z 2023 Final Year Project (FYP) Low, T. Z. H. (2023). Hybrid SLAM and object recognition on an embedded platform. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/171979 https://hdl.handle.net/10356/171979 en SCSE22-0772 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Low, Timothy Zhi Hao Hybrid SLAM and object recognition on an embedded platform |
| title | Hybrid SLAM and object recognition on an embedded platform |
| title_full | Hybrid SLAM and object recognition on an embedded platform |
| title_fullStr | Hybrid SLAM and object recognition on an embedded platform |
| title_full_unstemmed | Hybrid SLAM and object recognition on an embedded platform |
| title_short | Hybrid SLAM and object recognition on an embedded platform |
| title_sort | hybrid slam and object recognition on an embedded platform |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/171979 |
| work_keys_str_mv | AT lowtimothyzhihao hybridslamandobjectrecognitiononanembeddedplatform |