Leveraging cross-view geo-localization with ensemble learning and temporal awareness

被引:0
|
作者
Ghanem, Abdulrahman [1 ]
Abdelhay, Ahmed [1 ]
Salah, Noor Eldeen [1 ]
Nour Eldeen, Ahmed [1 ]
Elhenawy, Mohammed [2 ]
Masoud, Mahmoud [3 ]
Hassan, Ammar M. M. [4 ]
Hassan, Abdallah A. A. [1 ]
机构
[1] Minia Univ, Fac Engn, Comp & Syst Engn Dept, Al Minya, Egypt
[2] Queensland Univ Technol, Ctr Accid Res & Rd Safety Queensland CARRS Q, Brisbane, Australia
[3] King Fahd Univ Petr & Minerals, Interdisciplinary Res Ctr Smart Mobil & Logist, Dept Informat Syst & Operat Management, Dhahran, Saudi Arabia
[4] Arab Acad Sci Technol & Maritime Transport, South Valley Branch, Aswan, Egypt
来源
PLOS ONE | 2023年 / 18卷 / 03期
关键词
D O I
10.1371/journal.pone.0283672
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
The Global Navigation Satellite System (GNSS) is unreliable in some situations. To mend the poor GNSS signal, an autonomous vehicle can self-localize by matching a ground image against a database of geotagged aerial images. However, this approach has challenges because of the dramatic differences in the viewpoint between aerial and ground views, harsh weather and lighting conditions, and the lack of orientation information in training and deployment environments. In this paper, it is shown that previous models in this area are complementary, not competitive, and that each model solves a different aspect of the problem. There was a need for a holistic approach. An ensemble model is proposed to aggregate the predictions of multiple independently trained state-of-the-art models. Previous state-of-the-art (SOTA) temporal-aware models used heavy-weight network to fuse the temporal information into the query process. The effect of making the query process temporal-aware is explored and exploited by an efficient meta block: naive history. But none of the existing benchmark datasets was suitable for extensive temporal awareness experiments, a new derivative dataset based on the BDD100K dataset is generated. The proposed ensemble model achieves a recall accuracy R@1 (Recall@1: the top most prediction) of 97.74% on the CVUSA dataset and 91.43% on the CVACT dataset (surpassing the current SOTA). The temporal awareness algorithm converges to R@1 of 100% by looking at a few steps back in the trip history.
引用
收藏
页数:23
相关论文
共 50 条
  • [1] Cross-View Geo-Localization: A Survey
    Durgam, Abhilash
    Paheding, Sidike
    Dhiman, Vikas
    Devabhaktuni, Vijay
    IEEE ACCESS, 2024, 12 : 192028 - 192050
  • [2] Cross-View Image Sequence Geo-localization
    Zhang, Xiaohan
    Sultani, Waqas
    Wshah, Safwan
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 2913 - 2922
  • [3] GAMa: Cross-View Video Geo-Localization
    Vyas, Shruti
    Chen, Chen
    Shah, Mubarak
    COMPUTER VISION, ECCV 2022, PT XXXVII, 2022, 13697 : 440 - 456
  • [4] Cross-view geo-localization with evolving transformer
    Yang, Hongji
    Lu, Xiufan
    Zhu, Yingying
    arXiv, 2021,
  • [5] Learning Cross-View Visual Geo-Localization Without Ground Truth
    Li, Haoyuan
    Xu, Chang
    Yang, Wen
    Yu, Huai
    Xia, Gui-Song
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 1
  • [6] Joint Representation Learning and Keypoint Detection for Cross-View Geo-Localization
    Lin, Jinliang
    Zheng, Zhedong
    Zhong, Zhun
    Luo, Zhiming
    Li, Shaozi
    Yang, Yi
    Sebe, Nicu
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 3780 - 3792
  • [7] MUTUAL RELATIVE POSITION LEARNING TRANSFORMER FOR CROSS-VIEW GEO-LOCALIZATION
    Gu, Bo
    Ling, Hefei
    Shi, Yuxuan
    Li, Zongyi
    Zhao, Chuang
    Li, Ping
    Cao, Qiang
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 286 - 290
  • [8] Learning Robust Feature Representation for Cross-View Image Geo-Localization
    Gan, Wenjian
    Zhou, Yang
    Hu, Xiaofei
    Zhao, Luying
    Huang, Gaoshuang
    Hou, Mingbo
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2025, 22
  • [9] Benchmarking the Robustness of Cross-View Geo-Localization Models
    Zhang, Qingwang
    Zhu, Yingying
    COMPUTER VISION - ECCV 2024, PT LXXXVII, 2025, 15145 : 36 - 53
  • [10] Dual Path Network for Cross-view Geo-Localization
    Dong, Leyi
    Wang, Yuhui
    Huang, Junshi
    Qian, Xueming
    Fan, Mingyuan
    Lai, Shenqi
    PROCEEDINGS OF THE 2023 WORKSHOP ON UAVS IN MULTIMEDIA: CAPTURING THE WORLD FROM A NEW PERSPECTIVE, UAVM 2023, 2023, : 45 - 49