Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud

Place recognition is an important task in the computer vision and robotics communities, with a wild application in many fields. For unmanned vehicle, 3D LiDAR and semantic point cloud is always used for place recognition. Recent state-of-the-art works mostly focus on structural design of the network...

Full description

Saved in:
Bibliographic Details
Main Author: Zhao, Yangyang
Other Authors: Wang Dan Wei
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/173189
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-173189
record_format dspace
spelling sg-ntu-dr.10356-1731892024-01-19T15:45:31Z Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud Zhao, Yangyang Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Place recognition is an important task in the computer vision and robotics communities, with a wild application in many fields. For unmanned vehicle, 3D LiDAR and semantic point cloud is always used for place recognition. Recent state-of-the-art works mostly focus on structural design of the network. This dissertation introduces relation-based and response-based self-knowledge distillation into the training process and further proposes an instance-to-region supervised knowledge distillation method based on MinkLoc3Dv2 backbone. Experimental evaluation shows excellent performance and generalization on standard benchmarks. Master's degree 2024-01-17T02:30:56Z 2024-01-17T02:30:56Z 2023 Thesis-Master by Coursework Zhao, Y. (2023). Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/173189 https://hdl.handle.net/10356/173189 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
Zhao, Yangyang
Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
description Place recognition is an important task in the computer vision and robotics communities, with a wild application in many fields. For unmanned vehicle, 3D LiDAR and semantic point cloud is always used for place recognition. Recent state-of-the-art works mostly focus on structural design of the network. This dissertation introduces relation-based and response-based self-knowledge distillation into the training process and further proposes an instance-to-region supervised knowledge distillation method based on MinkLoc3Dv2 backbone. Experimental evaluation shows excellent performance and generalization on standard benchmarks.
author2 Wang Dan Wei
author_facet Wang Dan Wei
Zhao, Yangyang
format Thesis-Master by Coursework
author Zhao, Yangyang
author_sort Zhao, Yangyang
title Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
title_short Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
title_full Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
title_fullStr Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
title_full_unstemmed Place recognition for unmanned vehicle based on 3D LiDAR and semantic point cloud
title_sort place recognition for unmanned vehicle based on 3d lidar and semantic point cloud
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/173189
_version_ 1789483223811620864