國立高雄大學圖資館 |

Language: English

Back

Data-Driven Geometric Workflows for Camera Localization.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Data-Driven Geometric Workflows for Camera Localization.
Author:	Min, Zhixiang.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2023
Description:	130 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Notes:	Advisor: Dunn, Enrique.
Contained By:	Dissertations Abstracts International85-04B.
Subject:	Computer science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30521883
ISBN:	9798380581202

Data-Driven Geometric Workflows for Camera Localization.
Min, Zhixiang.

Data-Driven Geometric Workflows for Camera Localization. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 130 p.

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--Stevens Institute of Technology, 2023.

This item must not be sold to any third party vendors.

Visual localization aims to estimate the spatial relationship between a camera and its environment based on captured visual media. However, the increasing demand for robustness in challenging environments and the requirement to solve semantic-centric problems present significant challenges for geometric localization workflows. Conventional methods rely on hand-crafted heuristics, which often struggle to meet the growing demands of such environments. On the other hand, emerging deep learning methods face issues with generalization and interpretability due to their inherently geometry-agnostic nature. To address these challenges, this dissertation presents a hybrid localization workflow that leverages both geometric and data-driven priors. We summarize four of our works that have achieved remarkable progress in terms of robustness, accuracy, and interpretability, by utilizing our proposed workflow. These four works span across different fields, including visual odometry, object localization, floor plan localization, and viewpoint learning. 

ISBN: 9798380581202Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

Floor plan localization

Data-Driven Geometric Workflows for Camera Localization.
LDR:02281nmm a2200397 4500 001 655784
005 20240414211929.5
006 m o d
007 cr#unu||||||||
008 240620s2023 ||||||||||||||||| ||eng d
020 $a 9798380581202
035 $a (MiAaPQ)AAI30521883
035 $a AAI30521883
040 $a MiAaPQ $c MiAaPQ
100 1 $a Min, Zhixiang. $3 966867
245 1 0 $a Data-Driven Geometric Workflows for Camera Localization.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 130 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Dunn, Enrique.
502 $a Thesis (Ph.D.)--Stevens Institute of Technology, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Visual localization aims to estimate the spatial relationship between a camera and its environment based on captured visual media. However, the increasing demand for robustness in challenging environments and the requirement to solve semantic-centric problems present significant challenges for geometric localization workflows. Conventional methods rely on hand-crafted heuristics, which often struggle to meet the growing demands of such environments. On the other hand, emerging deep learning methods face issues with generalization and interpretability due to their inherently geometry-agnostic nature. To address these challenges, this dissertation presents a hybrid localization workflow that leverages both geometric and data-driven priors. We summarize four of our works that have achieved remarkable progress in terms of robustness, accuracy, and interpretability, by utilizing our proposed workflow. These four works span across different fields, including visual odometry, object localization, floor plan localization, and viewpoint learning. 
590 $a School code: 0733.
650 4 $a Computer science. $3 199325
650 4 $a Computer engineering. $3 212944
650 4 $a Information technology. $3 184390
653 $a Floor plan localization
653 $a Object localization
653 $a Viewpoint learning
653 $a Visual localization
653 $a Visual odometry
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a Stevens Institute of Technology. $b Computer Science. $3 966868
773 0 $t Dissertations Abstracts International $g 85-04B.
790 $a 0733
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30521883