Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces

Janghun Hyeon; Bumchul Jang; Hyunga Choi; Joohyung Kim; Dongwoo Kim; Nakju Doh

doi:10.1016/j.engappai.2023.106256

Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces

Janghun Hyeon, Bumchul Jang, Hyunga Choi, Joohyung Kim, Dongwoo Kim, Nakju Doh

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

This study presents a novel and reliable visual positioning system (VPS), KR-Net, for kidnap recovery tasks, which predicts an accurate position when a robot is first initiated. KR-Net is based on a hierarchical visual localization method and demonstrates significant robustness in large-scale indoor environments. The proposed VPS utilizes a photo-realistic 3D model to generate a dense database of any camera pose and incorporates a novel global descriptor for indoor spaces, i-GeM, that outperforms existing methods in terms of robustness. Additionally, the proposed combinatorial pooling approach overcomes the limitations of previous single image-based predictions in large-scale indoor environments, allowing for accurate discrimination between similar locations. Extensive evaluations were performed on six large-scale indoor datasets to demonstrate the contributions of each component. To the best of our knowledge, KR-Net is the first system to estimate wake-up positions with a near 100% confidence level within a 1.0m distance error threshold.

Original language	English
Article number	106256
Journal	Engineering Applications of Artificial Intelligence
Volume	123
DOIs	https://doi.org/10.1016/j.engappai.2023.106256
Publication status	Published - 2023 Aug

Bibliographical note

Funding Information:
We would like to thank Dong Hoon Yi, Kyungho Yoo, and Jeongae Choi, who work for LG Electronics for their help in conducting this study. This research was supported by multiple research funds from Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Republic of Korea ( NRF-2022R1A6A3A01087592 ), National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (Project Number: 2022R1F1A1073972), and Teelabs.

Publisher Copyright:
© 2023 Elsevier Ltd

Keywords

Camera pose estimation
Image retrieval
Indoor spaces
Place recognition
Visual localization
Visual positioning systems

ASJC Scopus subject areas

Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1016/j.engappai.2023.106256

Cite this

@article{3fee95d3d37c417fb950cc1233fcb25b,

title = "Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces",

abstract = "This study presents a novel and reliable visual positioning system (VPS), KR-Net, for kidnap recovery tasks, which predicts an accurate position when a robot is first initiated. KR-Net is based on a hierarchical visual localization method and demonstrates significant robustness in large-scale indoor environments. The proposed VPS utilizes a photo-realistic 3D model to generate a dense database of any camera pose and incorporates a novel global descriptor for indoor spaces, i-GeM, that outperforms existing methods in terms of robustness. Additionally, the proposed combinatorial pooling approach overcomes the limitations of previous single image-based predictions in large-scale indoor environments, allowing for accurate discrimination between similar locations. Extensive evaluations were performed on six large-scale indoor datasets to demonstrate the contributions of each component. To the best of our knowledge, KR-Net is the first system to estimate wake-up positions with a near 100% confidence level within a 1.0m distance error threshold.",

keywords = "Camera pose estimation, Image retrieval, Indoor spaces, Place recognition, Visual localization, Visual positioning systems",

author = "Janghun Hyeon and Bumchul Jang and Hyunga Choi and Joohyung Kim and Dongwoo Kim and Nakju Doh",

note = "Funding Information: We would like to thank Dong Hoon Yi, Kyungho Yoo, and Jeongae Choi, who work for LG Electronics for their help in conducting this study. This research was supported by multiple research funds from Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Republic of Korea ( NRF-2022R1A6A3A01087592 ), National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (Project Number: 2022R1F1A1073972), and Teelabs. Publisher Copyright: {\textcopyright} 2023 Elsevier Ltd",

year = "2023",

month = aug,

doi = "10.1016/j.engappai.2023.106256",

language = "English",

volume = "123",

journal = "Engineering Applications of Artificial Intelligence",

issn = "0952-1976",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces

AU - Hyeon, Janghun

AU - Jang, Bumchul

AU - Choi, Hyunga

AU - Kim, Joohyung

AU - Kim, Dongwoo

AU - Doh, Nakju

N1 - Funding Information: We would like to thank Dong Hoon Yi, Kyungho Yoo, and Jeongae Choi, who work for LG Electronics for their help in conducting this study. This research was supported by multiple research funds from Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Republic of Korea ( NRF-2022R1A6A3A01087592 ), National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (Project Number: 2022R1F1A1073972), and Teelabs. Publisher Copyright: © 2023 Elsevier Ltd

PY - 2023/8

Y1 - 2023/8

N2 - This study presents a novel and reliable visual positioning system (VPS), KR-Net, for kidnap recovery tasks, which predicts an accurate position when a robot is first initiated. KR-Net is based on a hierarchical visual localization method and demonstrates significant robustness in large-scale indoor environments. The proposed VPS utilizes a photo-realistic 3D model to generate a dense database of any camera pose and incorporates a novel global descriptor for indoor spaces, i-GeM, that outperforms existing methods in terms of robustness. Additionally, the proposed combinatorial pooling approach overcomes the limitations of previous single image-based predictions in large-scale indoor environments, allowing for accurate discrimination between similar locations. Extensive evaluations were performed on six large-scale indoor datasets to demonstrate the contributions of each component. To the best of our knowledge, KR-Net is the first system to estimate wake-up positions with a near 100% confidence level within a 1.0m distance error threshold.

AB - This study presents a novel and reliable visual positioning system (VPS), KR-Net, for kidnap recovery tasks, which predicts an accurate position when a robot is first initiated. KR-Net is based on a hierarchical visual localization method and demonstrates significant robustness in large-scale indoor environments. The proposed VPS utilizes a photo-realistic 3D model to generate a dense database of any camera pose and incorporates a novel global descriptor for indoor spaces, i-GeM, that outperforms existing methods in terms of robustness. Additionally, the proposed combinatorial pooling approach overcomes the limitations of previous single image-based predictions in large-scale indoor environments, allowing for accurate discrimination between similar locations. Extensive evaluations were performed on six large-scale indoor datasets to demonstrate the contributions of each component. To the best of our knowledge, KR-Net is the first system to estimate wake-up positions with a near 100% confidence level within a 1.0m distance error threshold.

KW - Camera pose estimation

KW - Image retrieval

KW - Indoor spaces

KW - Place recognition

KW - Visual localization

KW - Visual positioning systems

UR - http://www.scopus.com/inward/record.url?scp=85151798675&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2023.106256

DO - 10.1016/j.engappai.2023.106256

M3 - Article

AN - SCOPUS:85151798675

SN - 0952-1976

VL - 123

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

M1 - 106256

ER -

Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this