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 journalArticlepeer-review

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 languageEnglish
Article number106256
JournalEngineering Applications of Artificial Intelligence
Volume123
DOIs
Publication statusPublished - 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

Fingerprint

Dive into the research topics of 'Photo-realistic 3D model based accurate visual positioning system for large-scale indoor spaces'. Together they form a unique fingerprint.

Cite this