A Low-Cost and Scalable Framework to Build Large-Scale Localization Benchmark for Augmented Reality

被引:5
|
作者
Liu, Haomin [1 ,2 ]
Zhao, Linsheng [3 ]
Peng, Zhen [3 ]
Xie, Weijian [3 ]
Jiang, Mingxuan [3 ]
Zha, Hongbin [1 ]
Bao, Hujun [4 ]
Zhang, Guofeng [4 ]
机构
[1] Peking Univ, Sch Intelligence Sci & Technol, Beijing 100871, Peoples R China
[2] SenseTime Res, Beijing 100190, Peoples R China
[3] SenseTime Res, Hangzhou 311215, Peoples R China
[4] Zhejiang Univ, State Key Lab CAD & CG, Hangzhou 310058, Peoples R China
关键词
Location awareness; Visualization; Simultaneous localization and mapping; Costs; Benchmark testing; Laser radar; Global Positioning System; Augmented reality (AR); benchmark; SLAM; visual localization; indoor localization; MONOCULAR SLAM; MAGNETIC-FIELD; ROBUST; VERSATILE;
D O I
10.1109/TCSVT.2023.3306160
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Nowadays the application of AR is expanding from small or medium environments to large-scale environments, where the visual-based localization in the large-scale environments becomes a critical demand. Current visual-based localization techniques face robustness challenges in complex large-scale environments, requiring tremendous number of data with groundtruth localization for algorithm benchmarking or model training. The previous groundtruth solutions can only be used outdoors, or require high equipment/labor costs, so they cannot be scalable to large environments for both indoors and outdoors, nor can they produce large amounts of data at a feasible cost. In this work, we propose LSFB, a novel low-cost and scalable framework to build localization benchmark in large-scale indoor and outdoor environments. The key is to reconstruct an accurate HD map of the environment. For each visual-inertial sequence captured in the environment, the groundtruth poses are obtained by joint optimization taking both the HD map and visual-inertial constraints. The experiments demonstrate the obtained groundtruth poses have cm-level accuracy. We use the proposed method to collect a localization dataset by mobile phones and AR glasses in various environments with various motions, and release the dataset as the first large-scale localization benchmark for AR.
引用
收藏
页码:2274 / 2288
页数:15
相关论文
共 50 条
  • [41] Augmented Reality for Robot Control in Low-cost Automation Context and IoT
    Caiza, Gustavo
    Bonilla-Vasconez, Pablo
    Garcia, Carlos A.
    Garcia, Marcelo, V
    2020 25TH IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA), 2020, : 1457 - 1460
  • [42] A Low-cost, High-efficiency SDN Framework to Diminish Redundant ARP and IGMP Traffics in Large-scale LANs
    Wang, You-Chiun
    Hu, Han
    2018 IEEE 42ND ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 1, 2018, : 894 - 903
  • [43] Internet virtual studio: Low-cost augmented reality system for WebTV
    Sitnik, Robert
    Pasko, Slawomir
    Karaszewski, Maciej
    Witkowski, Marcin
    ENGINEERING REALITY OF VIRTUAL REALITY 2008, 2008, 6804
  • [44] A low-cost virtual studio based on Augmented Reality for video production
    Aguilar, Ivan A.
    Sementille, Antonio C.
    Sanches, Silvio R. R.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (23) : 33899 - 33920
  • [45] An Augmented Reality Geo-Registration Method for Ground Target Localization from a Low-Cost UAV Platform
    Ren, Xiang
    Sun, Min
    Jiang, Cheng
    Liu, Lei
    Huang, Wei
    SENSORS, 2018, 18 (11)
  • [46] Low-cost mobile augmented reality service for building information modeling
    Um, Jumyung
    Park, Joung Min
    Park, Seo Yeon
    Yilmaz, Gokcen
    AUTOMATION IN CONSTRUCTION, 2023, 146
  • [47] NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
    Wang, Qi
    Gao, Junyu
    Lin, Wei
    Li, Xuelong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (06) : 2141 - 2149
  • [48] Scalable and low-cost acoustic source localization for wireless sensor networks
    You, YoungBin
    Cha, HoJung
    UBIQUITOUS INTELLIGENCE AND COMPUTING, PROCEEDINGS, 2006, 4159 : 517 - 526
  • [49] UbiTrack: Enabling Scalable & Low-Cost Device Localization with Onboard WiFi
    Wang, Wenpeng
    Liu, Zetian
    Gao, Jiechao
    Saoda, Nurani
    Campbell, Bradford
    BUILDSYS'21: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILT ENVIRONMENTS, 2021, : 11 - 20
  • [50] Large-scale synthesis of low-cost bimetallic polyphthalocyanine for highly stable water oxidation
    Qi, Qianglong
    Hu, Jue
    Guo, Sitian
    Song, Hongchuan
    Wang, Shixing
    Yao, Yaochun
    Le, Thiquynhxuan
    Li, Wei
    Zhang, Chengxu
    Zhang, Libo
    APPLIED CATALYSIS B-ENVIRONMENTAL, 2021, 299