EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond Spatial Domain: Multi-View Geo-Localization with Frequency-Based Positive-Incentive Information Screening

Bangyong Sun, Mian Li, Bo Sun, Ganchao Liu, Cheng Bi, Weifeng Wang, Xiangpeng Feng, Geng Zhang, Bingliang Hu

Remote Sensing · 26.12.2025 · 18 (1) · 88

DOI: 10.3390/rs18010088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.12.2025. Verfasst von Bangyong Sun und 8 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Project of Shaanxi Province, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The substantial domain discrepancy inherent in multi-source and multi-view imagery presents formidable challenges to achieving precise drone-based multi-view geo-localization. Existing methodologies primarily focus on designing sophisticated backbone architectures to extract view-invariant representations within abstract feature spaces, yet they often overlook the rich and discriminative frequency-domain cues embedded in multi-view data. Inspired by the principles of π-Noise theory, this paper proposes a frequency-domain Positive-Incentive Information Screening (PIIS) mechanism that adaptively identifies and preserves task-relevant frequency components based on entropy-guided information metrics. This principled approach selectively enhances discriminative spectral signatures while suppressing redundant or noisy components, thereby improving multi-view feature alignment under substantial appearance and geometric variations. The proposed PIIS strategy demonstrates strong architectural generality, as it can be seamlessly integrated into various backbone networks including convolutional-based and Transformer-based architectures while maintaining consistent performance improvements across different models. Extensive evaluations on the University-1652 and SUES-200 datasets have validated the great potential of the proposed method. Specifically, the PIIS-N model achieves a Recall@1 of 94.56% and a mean Average Precision (mAP) of 95.44% on the University-1652 dataset, exhibiting competitive accuracy among contemporary approaches. These findings underscore the considerable promise of frequency-domain analysis in advancing multi-view geo-localization.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Project of Shaanxi Province
  • China Postdoctoral Science Foundation
  • Open Research Fund of Shaanxi Key Laboratory of Optical Remote Sensing and Intelligent Information Processing

Zitieren

APA

Sun, B., Li, M., Sun, B., Liu, G., Bi, C., Wang, W., Feng, X., Zhang, G., & Hu, B. (2025). Beyond Spatial Domain: Multi-View Geo-Localization with Frequency-Based Positive-Incentive Information Screening. Remote Sensing, 18(1), 88. https://doi.org/10.3390/rs18010088

Vancouver

Sun B, Li M, Sun B, Liu G, Bi C, Wang W, et al. Beyond Spatial Domain: Multi-View Geo-Localization with Frequency-Based Positive-Incentive Information Screening. Remote Sensing. 2025;18(1):88. doi:10.3390/rs18010088

BibTeX
@article{Sun2025,
  author = {Sun, Bangyong and Li, Mian and Sun, Bo and Liu, Ganchao and Bi, Cheng and Wang, Weifeng and Feng, Xiangpeng and Zhang, Geng and Hu, Bingliang},
  title = {Beyond Spatial Domain: Multi-View Geo-Localization with Frequency-Based Positive-Incentive Information Screening},
  journal = {Remote Sensing},
  year = {2025},
  volume = {18},
  number = {1},
  pages = {88},
  doi = {10.3390/rs18010088}
}
Kostenlos starten →