Real-time visual localization system on an embedded platform

Simultaneous localization and mapping (SLAM) of an unknown environment is an important task for mobile autonomous robots and navigation systems. Indoor SLAM, however, cannot rely on GPS signal and existing solutions often assume static scene conditions which may not occur in real-life scenarios. In...

Full description

Saved in:
Bibliographic Details
Main Author: Do, Anh Tu
Other Authors: Lam Siew Kei
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148230
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-148230
record_format dspace
spelling sg-ntu-dr.10356-1482302021-04-29T00:21:31Z Real-time visual localization system on an embedded platform Do, Anh Tu Lam Siew Kei School of Computer Science and Engineering ASSKLam@ntu.edu.sg Engineering::Computer science and engineering::Computer systems organization::Special-purpose and application-based systems Simultaneous localization and mapping (SLAM) of an unknown environment is an important task for mobile autonomous robots and navigation systems. Indoor SLAM, however, cannot rely on GPS signal and existing solutions often assume static scene conditions which may not occur in real-life scenarios. In addition, the maps generated using typical SLAM systems have no semantic meaning of the environment and are not useful for higher level mission such as path planning, object interaction, etc. The computation cost of such system is another concern as SLAM systems are often implemented on embedded platforms. In this project, two real-time visual SLAM systems are designed for the Jetson Xavier NX embedded platform that are capable of working in dynamic environments and generating 3D semantic global maps for context-aware tasks. It employs deep neural network for obtaining semantic information to build the global maps. A distributed computing setup is also considered in order to achieve real-time 3D semantic map generation. The quantitative and qualitative results of the proposed semantic SLAM systems are presented for comparison and evaluation. Bachelor of Engineering (Computer Engineering) 2021-04-29T00:20:34Z 2021-04-29T00:20:34Z 2021 Final Year Project (FYP) Do, A. T. (2021). Real-time visual localization system on an embedded platform. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148230 https://hdl.handle.net/10356/148230 en SCSE20-0144 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computer systems organization::Special-purpose and application-based systems
spellingShingle Engineering::Computer science and engineering::Computer systems organization::Special-purpose and application-based systems
Do, Anh Tu
Real-time visual localization system on an embedded platform
description Simultaneous localization and mapping (SLAM) of an unknown environment is an important task for mobile autonomous robots and navigation systems. Indoor SLAM, however, cannot rely on GPS signal and existing solutions often assume static scene conditions which may not occur in real-life scenarios. In addition, the maps generated using typical SLAM systems have no semantic meaning of the environment and are not useful for higher level mission such as path planning, object interaction, etc. The computation cost of such system is another concern as SLAM systems are often implemented on embedded platforms. In this project, two real-time visual SLAM systems are designed for the Jetson Xavier NX embedded platform that are capable of working in dynamic environments and generating 3D semantic global maps for context-aware tasks. It employs deep neural network for obtaining semantic information to build the global maps. A distributed computing setup is also considered in order to achieve real-time 3D semantic map generation. The quantitative and qualitative results of the proposed semantic SLAM systems are presented for comparison and evaluation.
author2 Lam Siew Kei
author_facet Lam Siew Kei
Do, Anh Tu
format Final Year Project
author Do, Anh Tu
author_sort Do, Anh Tu
title Real-time visual localization system on an embedded platform
title_short Real-time visual localization system on an embedded platform
title_full Real-time visual localization system on an embedded platform
title_fullStr Real-time visual localization system on an embedded platform
title_full_unstemmed Real-time visual localization system on an embedded platform
title_sort real-time visual localization system on an embedded platform
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/148230
_version_ 1698713692273639424