Place recognition using line-junction-lines in urban environments

Place recognition plays a vital role in eliminating accumulated drift from visual odometry in SLAM system. Bag- of-Words (BoW) -based approach is the most popular solution due to its efficiency and robustness. We propose to use Line- Junction-Line (LJL) to build a BoW for place recognition in urban...

Full description

Saved in:
Bibliographic Details
Main Authors: Tang, Xiaoyu, Fu, Wenhao, Jiang, Muyun, Peng, Guohao, Wu, Zhenyu, Yue, Yufeng, Wang, Danwei
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/141837
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-141837
record_format dspace
spelling sg-ntu-dr.10356-1418372020-06-11T03:31:52Z Place recognition using line-junction-lines in urban environments Tang, Xiaoyu Fu, Wenhao Jiang, Muyun Peng, Guohao Wu, Zhenyu Yue, Yufeng Wang, Danwei School of Electrical and Electronic Engineering 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM) ST Engineering-NTU Corporate Laboratory Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Place Recognition Structural Information Place recognition plays a vital role in eliminating accumulated drift from visual odometry in SLAM system. Bag- of-Words (BoW) -based approach is the most popular solution due to its efficiency and robustness. We propose to use Line- Junction-Line (LJL) to build a BoW for place recognition in urban environments. LJL is a simple structure of two lines with their intersection. Different from point features which are detected based on pixel intensity patterns, it represents structure with physical existence, which is more robust to challenging scenarios. Moreover, its descriptor is distinctive and encodes the relationship between the two lines. Experiments on KITTI dataset show the effectiveness of the proposed method compared to loop detection using BoW trained with either point or line features. NRF (Natl Research Foundation, S’pore) Accepted version 2020-06-11T03:31:52Z 2020-06-11T03:31:52Z 2020 Conference Paper Tang, X., Fu, W., Jiang, M., Peng, G., Wu, Z., Yue, Y., & Wang, D. (2019). Place recognition using line-junction-lines in urban environments. Proceedings of 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), 530-535. doi:10.1109/CIS-RAM47153.2019.9095776 978-1-7281-3459-8 https://hdl.handle.net/10356/141837 10.1109/CIS-RAM47153.2019.9095776 530 535 en SRP5 © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/CIS-RAM47153.2019.9095776 application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
Place Recognition
Structural Information
spellingShingle Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
Place Recognition
Structural Information
Tang, Xiaoyu
Fu, Wenhao
Jiang, Muyun
Peng, Guohao
Wu, Zhenyu
Yue, Yufeng
Wang, Danwei
Place recognition using line-junction-lines in urban environments
description Place recognition plays a vital role in eliminating accumulated drift from visual odometry in SLAM system. Bag- of-Words (BoW) -based approach is the most popular solution due to its efficiency and robustness. We propose to use Line- Junction-Line (LJL) to build a BoW for place recognition in urban environments. LJL is a simple structure of two lines with their intersection. Different from point features which are detected based on pixel intensity patterns, it represents structure with physical existence, which is more robust to challenging scenarios. Moreover, its descriptor is distinctive and encodes the relationship between the two lines. Experiments on KITTI dataset show the effectiveness of the proposed method compared to loop detection using BoW trained with either point or line features.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Tang, Xiaoyu
Fu, Wenhao
Jiang, Muyun
Peng, Guohao
Wu, Zhenyu
Yue, Yufeng
Wang, Danwei
format Conference or Workshop Item
author Tang, Xiaoyu
Fu, Wenhao
Jiang, Muyun
Peng, Guohao
Wu, Zhenyu
Yue, Yufeng
Wang, Danwei
author_sort Tang, Xiaoyu
title Place recognition using line-junction-lines in urban environments
title_short Place recognition using line-junction-lines in urban environments
title_full Place recognition using line-junction-lines in urban environments
title_fullStr Place recognition using line-junction-lines in urban environments
title_full_unstemmed Place recognition using line-junction-lines in urban environments
title_sort place recognition using line-junction-lines in urban environments
publishDate 2020
url https://hdl.handle.net/10356/141837
_version_ 1681059622948962304