EUVIMEDEUVIMED entdecken
Crossref

GeoDTR+: Toward Generic Cross-View Geolocalization via Geometric Disentanglement

Xiaohan Zhang, Xingyu Li, Waqas Sultani, Chen Chen, Safwan Wshah

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10419-10433

DOI: 10.1109/tpami.2024.3443652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Xiaohan Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: NSF, National Oceanic and Atmospheric Administration, Vermont Advanced Computing Center.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-View Geo-Localization (CVGL) estimates the location of a ground image by matching it to a geo-tagged aerial image in a database. Recent works achieve outstanding progress on CVGL benchmarks. However, existing methods still suffer from poor performance in cross-area evaluation, in which the training and testing data are captured from completely distinct areas. We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models' overfitting to low-level details. Our preliminary work (Zhang et al. 2022) introduced a Geometric Layout Extractor (GLE) to capture the geometric layout from input features. However, the previous GLE does not fully exploit information in the input feature. In this work, we propose GeoDTR+ with an enhanced GLE module that better models the correlations among visual features. To fully explore the LS techniques from our preliminary work, we further propose Contrastive Hard Samples Generation (CHSG) to facilitate model training. Extensive experiments show that GeoDTR+ achieves state-of-the-art (SOTA) results in cross-area evaluation on CVUSA (Workman et al. 2015), CVACT (Liu and Li, 2019), and VIGOR (Zhu et al. 2021) by a large margin (16.44%, 22.71%, and 13.66% without polar transformation) while keeping the same-area performance comparable to existing SOTA. Moreover, we provide detailed analyses of GeoDTR+.

Förderung

  • NSF
  • National Oceanic and Atmospheric Administration
  • Vermont Advanced Computing Center
  • AMD's donation of critical hardware

Zitieren

APA

Zhang, X., Li, X., Sultani, W., Chen, C., & Wshah, S. (2024). GeoDTR+: Toward Generic Cross-View Geolocalization via Geometric Disentanglement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10419-10433. https://doi.org/10.1109/tpami.2024.3443652

Vancouver

Zhang X, Li X, Sultani W, Chen C, Wshah S. GeoDTR+: Toward Generic Cross-View Geolocalization via Geometric Disentanglement. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10419-10433. doi:10.1109/tpami.2024.3443652

BibTeX
@article{Zhang2024,
  author = {Zhang, Xiaohan and Li, Xingyu and Sultani, Waqas and Chen, Chen and Wshah, Safwan},
  title = {GeoDTR+: Toward Generic Cross-View Geolocalization via Geometric Disentanglement},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {10419--10433},
  doi = {10.1109/tpami.2024.3443652}
}
Kostenlos starten →