Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments

Currently, it is a norm to design a semiconductor fab using building information models (BIMs), which refer to a digital representation of a building’s physical and functional characteristics. The comprehensive data provided by BIMs include 3D geometric models. This paper presents a 3D mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Jeonghyeon Ahn, Jungho Ha, Jaemin Son, Junghyun Han
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10596301/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714525223256064
author Jeonghyeon Ahn
Jungho Ha
Jaemin Son
Junghyun Han
author_facet Jeonghyeon Ahn
Jungho Ha
Jaemin Son
Junghyun Han
author_sort Jeonghyeon Ahn
collection DOAJ
description Currently, it is a norm to design a semiconductor fab using building information models (BIMs), which refer to a digital representation of a building’s physical and functional characteristics. The comprehensive data provided by BIMs include 3D geometric models. This paper presents a 3D model-based camera tracking method, which is targeted at navigating a fab’s wide indoor environment. The key observation made in designing the method is that there are a number of fixed objects in such an indoor environment. The columns are the representative among them. Our method extracts the columns from the input image and matches them to their BIMs to estimate the camera pose. The estimation accuracy is significantly increased by adopting an instance segmentation network. It is trained with a dataset, which is extracted from the target indoor environment and processed by our own data engine. The test results show that our tracking method is drift-free, accurate and robust. We envision that it can be used in many applications such as AR-based visual inspection.
format Article
id doaj-art-4c170ad965bd4fbdafc99f1563ab1778
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4c170ad965bd4fbdafc99f1563ab17782025-08-20T03:13:40ZengIEEEIEEE Access2169-35362024-01-0112969119692310.1109/ACCESS.2024.342737810596301Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor EnvironmentsJeonghyeon Ahn0https://orcid.org/0009-0009-3761-9337Jungho Ha1https://orcid.org/0009-0009-6901-4957Jaemin Son2https://orcid.org/0009-0008-3764-0243Junghyun Han3https://orcid.org/0000-0001-6438-2974Department of Computer Science and Engineering, Korea University, Seoul, South KoreaDepartment of Computer Science and Engineering, Korea University, Seoul, South KoreaDepartment of Computer Science and Engineering, Korea University, Seoul, South KoreaDepartment of Computer Science and Engineering, Korea University, Seoul, South KoreaCurrently, it is a norm to design a semiconductor fab using building information models (BIMs), which refer to a digital representation of a building’s physical and functional characteristics. The comprehensive data provided by BIMs include 3D geometric models. This paper presents a 3D model-based camera tracking method, which is targeted at navigating a fab’s wide indoor environment. The key observation made in designing the method is that there are a number of fixed objects in such an indoor environment. The columns are the representative among them. Our method extracts the columns from the input image and matches them to their BIMs to estimate the camera pose. The estimation accuracy is significantly increased by adopting an instance segmentation network. It is trained with a dataset, which is extracted from the target indoor environment and processed by our own data engine. The test results show that our tracking method is drift-free, accurate and robust. We envision that it can be used in many applications such as AR-based visual inspection.https://ieeexplore.ieee.org/document/10596301/Augmented realitybuilding information modelingcamera trackinginstance segmentation
spellingShingle Jeonghyeon Ahn
Jungho Ha
Jaemin Son
Junghyun Han
Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
IEEE Access
Augmented reality
building information modeling
camera tracking
instance segmentation
title Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
title_full Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
title_fullStr Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
title_full_unstemmed Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
title_short Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments
title_sort model based segmentation supported camera tracking in fab x2019 s indoor environments
topic Augmented reality
building information modeling
camera tracking
instance segmentation
url https://ieeexplore.ieee.org/document/10596301/
work_keys_str_mv AT jeonghyeonahn modelbasedsegmentationsupportedcameratrackinginfabx2019sindoorenvironments
AT junghoha modelbasedsegmentationsupportedcameratrackinginfabx2019sindoorenvironments
AT jaeminson modelbasedsegmentationsupportedcameratrackinginfabx2019sindoorenvironments
AT junghyunhan modelbasedsegmentationsupportedcameratrackinginfabx2019sindoorenvironments