Deep learning feature-based visual SLAM

Visual SLAM is often used in autonomous agents for localization and mapping. A key element of visual SLAM is the feature detector-descriptor used to extract tracking keypoints from images of the environment. Classical visual SLAM algorithms rely on hand-crafted methods, which have low computation...

Full description

Saved in:
Bibliographic Details
Main Author: Yong, Duan Kai
Other Authors: Lam Siew Kei
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/166008
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-166008
record_format dspace
spelling sg-ntu-dr.10356-1660082023-04-21T15:37:57Z Deep learning feature-based visual SLAM Yong, Duan Kai Lam Siew Kei School of Computer Science and Engineering ASSKLam@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Visual SLAM is often used in autonomous agents for localization and mapping. A key element of visual SLAM is the feature detector-descriptor used to extract tracking keypoints from images of the environment. Classical visual SLAM algorithms rely on hand-crafted methods, which have low computational complexity but suffer from poor accuracy. Deep-learned feature detector descriptors have the potential to improve feature accuracy and robustness and thus tracking performance. This paper aims to compare the advantages and disadvantages of classical and deeplearning feature detector-descriptors for use in mono-SLAM through a review of literature and comparing the experimental performance of ORB-SLAM2 and SuperPoint-SLAM. A broad set of experiments covering multiple conditions such as dynamic scenes, illumination changes, and fast motion have been performed to determine baseline performance as well as reveal which conditions favour each detector-descriptor type. Bachelor of Engineering (Computer Science) 2023-04-18T02:09:59Z 2023-04-18T02:09:59Z 2023 Final Year Project (FYP) Yong, D. K. (2023). Deep learning feature-based visual SLAM. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166008 https://hdl.handle.net/10356/166008 en 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::Computing methodologies::Image processing and computer vision
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Yong, Duan Kai
Deep learning feature-based visual SLAM
description Visual SLAM is often used in autonomous agents for localization and mapping. A key element of visual SLAM is the feature detector-descriptor used to extract tracking keypoints from images of the environment. Classical visual SLAM algorithms rely on hand-crafted methods, which have low computational complexity but suffer from poor accuracy. Deep-learned feature detector descriptors have the potential to improve feature accuracy and robustness and thus tracking performance. This paper aims to compare the advantages and disadvantages of classical and deeplearning feature detector-descriptors for use in mono-SLAM through a review of literature and comparing the experimental performance of ORB-SLAM2 and SuperPoint-SLAM. A broad set of experiments covering multiple conditions such as dynamic scenes, illumination changes, and fast motion have been performed to determine baseline performance as well as reveal which conditions favour each detector-descriptor type.
author2 Lam Siew Kei
author_facet Lam Siew Kei
Yong, Duan Kai
format Final Year Project
author Yong, Duan Kai
author_sort Yong, Duan Kai
title Deep learning feature-based visual SLAM
title_short Deep learning feature-based visual SLAM
title_full Deep learning feature-based visual SLAM
title_fullStr Deep learning feature-based visual SLAM
title_full_unstemmed Deep learning feature-based visual SLAM
title_sort deep learning feature-based visual slam
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/166008
_version_ 1764208155773894656