Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/153739
Title: DEEP LEARNING OF FEATURES FOR VISUAL LOCALIZATION
Authors: FENG MENGDAN
ORCID iD:   orcid.org/0000-0003-0401-9051
Keywords: visual localization, feature matching, deep learning, mobile robots, 2D-3D matching, mapping
Issue Date: 23-Aug-2018
Citation: FENG MENGDAN (2018-08-23). DEEP LEARNING OF FEATURES FOR VISUAL LOCALIZATION. ScholarBank@NUS Repository.
Abstract: Visual localization has attracted a lot of attention in recent years and is one of the most popular research topics in computer vision and robotics. Various literature has concerned about the visual localization issues in the fields of Structure-from-Motion (SfM), autonomous driving, virtual/augmented reality (VR/AR), etc. This Ph.D work focuses on developing efficient and effective algorithms for robust visual localization in outdoor environments. Three challenging topics are identified, i.e. long-term visual localization, precise 3D point cloud mapping and 2D-3D image to point cloud feature matching.
URI: https://scholarbank.nus.edu.sg/handle/10635/153739
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
FengMD.pdf8.2 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

50
checked on Jul 10, 2020

Download(s)

49
checked on Jul 10, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.