Indoor Topological Localization Using a Visual Landmark Sequence

被引:15
|
作者
Zhu, Jiasong [1 ,2 ]
Li, Qing [1 ,2 ,3 ,4 ,5 ]
Cao, Rui [1 ,2 ,4 ,5 ,6 ,7 ]
Sun, Ke [1 ,2 ]
Liu, Tao [8 ]
Garibaldi, Jonathan M. [3 ]
Li, Qingquan [1 ,2 ]
Liu, Bozhi [4 ,5 ]
Qiu, Guoping [3 ,4 ,5 ]
机构
[1] Shenzhen Univ, Shenzhen Key Lab Spatial Smart Sensing & Serv, Shenzhen 518060, Peoples R China
[2] Shenzhen Univ, Key Lab Geoenvironm Monitoring Coastal Zone, Natl Adm Surveying Mapping & Geoinformat, Shenzhen 518060, Peoples R China
[3] Univ Nottingham, Sch Comp Sci, Nottingham NG8 1BB, England
[4] Shenzhen Univ, Coll Informat Engn, Shenzhen 518060, Peoples R China
[5] Shenzhen Univ, Guangdong Key Lab Intelligent Informat Proc, Shenzhen 518060, Peoples R China
[6] Univ Nottingham Ningbo China, Int Doctoral Innovat Ctr, Ningbo 315100, Zhejiang, Peoples R China
[7] Univ Nottingham Ningbo China, Sch Comp Sci, Ningbo 315100, Zhejiang, Peoples R China
[8] Henan Univ Econ & Law, Coll Resource & Environm, Zhengzhou 450046, Henan, Peoples R China
基金
中国国家自然科学基金;
关键词
visual landmark sequence; indoor topological localization; convolutional neural network (CNN); second order hidden Markov model; NAVIGATION; RECOGNITION;
D O I
10.3390/rs11010073
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This paper presents a novel indoor topological localization method based on mobile phone videos. Conventional methods suffer from indoor dynamic environmental changes and scene ambiguity. The proposed Visual Landmark Sequence-based Indoor Localization (VLSIL) method is capable of addressing problems by taking steady indoor objects as landmarks. Unlike many feature or appearance matching-based localization methods, our method utilizes highly abstracted landmark sematic information to represent locations and thus is invariant to illumination changes, temporal variations, and occlusions. We match consistently detected landmarks against the topological map based on the occurrence order in the videos. The proposed approach contains two components: a convolutional neural network (CNN)-based landmark detector and a topological matching algorithm. The proposed detector is capable of reliably and accurately detecting landmarks. The other part is the matching algorithm built on the second order hidden Markov model and it can successfully handle the environmental ambiguity by fusing sematic and connectivity information of landmarks. To evaluate the method, we conduct extensive experiments on the real world dataset collected in two indoor environments, and the results show that our deep neural network-based indoor landmark detector accurately detects all landmarks and is expected to be utilized in similar environments without retraining and that VLSIL can effectively localize indoor landmarks.
引用
收藏
页数:24
相关论文
共 50 条
  • [41] Topological localization on indoor sonar based fuzzy maps
    Panzieri, S
    Petroselli, D
    Ulivi, G
    INTELLIGENT AUTONOMOUS SYSTEMS 6, 2000, : 596 - 603
  • [42] LOTR: Face Landmark Localization Using Localization Transformer
    Watchareeruetai, Ukrit
    Sommana, Benjaphan
    Jain, Sanjana
    Noinongyao, Pavit
    Ganguly, Ankush
    Samacoits, Aubin
    Earp, Samuel W. F.
    Sritrakool, Nakarin
    IEEE Access, 2022, 10 : 16530 - 16543
  • [43] A wearable interface for topological mapping and localization in indoor environments
    Schindler, Grant
    Metzger, Christian
    Starner, Thad
    LOCATION- AND CONTEXT-AWARENESS, PROCEEDINGS, 2006, 3987 : 64 - 73
  • [44] Topological navigation and qualitative localization for indoor environment using multi-sensory perception
    Ranganathan, P
    Hayet, JB
    Devy, M
    Hutchinson, S
    Lerasle, F
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2002, 41 (2-3) : 137 - 144
  • [45] Indoor Localization Method Based on Sequential Motion Tracking Using Topological Path Map
    Lee, Yu-Cheol
    Myung, Hyun
    IEEE ACCESS, 2019, 7 : 46187 - 46197
  • [46] Indoor Localization With Adaptive Signal Sequence Representations
    Liu, Ning
    He, Tao
    He, Suining
    Niu, Qun
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (11) : 11678 - 11694
  • [47] Landmark Sequence Data Association for Simultaneous Localization and Mapping of Robots
    Yi, Yingmin
    Huang, Ying
    CYBERNETICS AND INFORMATION TECHNOLOGIES, 2014, 14 (03) : 86 - 95
  • [48] Analysis of Visual Landmark Detectors and Descriptors in SLAM in Indoor and Outdoor Environments
    Ballesta, M.
    Gil, A.
    Reinoso, O.
    Ubeda, D.
    REVISTA IBEROAMERICANA DE AUTOMATICA E INFORMATICA INDUSTRIAL, 2010, 7 (02): : 68 - +
  • [49] A Visual Localization System for Complex Indoor Environment
    Jiang, X.L.
    Liu, Chao-Yang
    Deng, Hongbin
    Lecture Notes in Electrical Engineering, 2023, 1010 LNEE : 1482 - 1492
  • [50] Indoor Localization Solution for Users with Visual Disabilities
    Calle-Jimenez, Tania
    Sanchez-Gordon, Sandra
    Lujan-Mora, Sergio
    PROCEEDINGS 3RD INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND COMPUTER SCIENCE (INCISCOS 2018), 2018, : 205 - 212