A Cross-Attention and Deformable Convolution Approach for Generating Invariant Descriptors in Visual Geolocation Tasks
Programmnaya Ingeneria · 14.04.2026 · 17 (4) · 191-200
DOI: 10.17587/prin.17.191-200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Programmnaya Ingeneria, erschienen am 14.04.2026. Verfasst von S. A. Morozov und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This article addresses the critical task of visual geolocalization for unmanned aerial vehicles (UAVs) in GNSS-denied environments. It focuses on overcoming the limitations of classical feature-based methods, which are highly sensitive to photometric and textural variations in aerial images captured at different times and under different conditions. The paper proposes a comprehensive approach based on a novel convolutional neural network, CADE-Net, which introduces an integration of an adaptive architecture, a cross-attention mechanism, and a hybrid loss function. The core challenge lies in matching a current onboard aerial image against a georeferenced satellite or aerial map from a database despite significant changes caused by varying seasons, weather, and lighting conditions. The proposed CADE-Net architecture is specifically designed to tackle these challenges. It employs a two-stream structure with deformable convolutions to achieve geometric invariance to scale and rotation. Furthermore, a cross-attention mechanism is integrated between the streams to explicitly model the relationships between image pairs, enabling the network to focus on semantically correspondent regions despite their visual differences. The training process is enhanced by a hybrid loss function that combines metric learning principles with an adversarial approach. A key innovation is the intelligent mining strategy for hard negatives, which forces the model to learn fine-grained details by distinguishing between structurally similar but semantically different objects. Proposed approach can generate robust, invariant features that are resilient to complex, non-linear distortions. This work is of significant practical importance for developing fully autonomous and reliable UAV navigation systems capable of operating effectively without GNSS signals.
Zitieren
APA
Morozov, S. A., Rokhlin, D. E., & Skorniakova, E. A. (2026). A Cross-Attention and Deformable Convolution Approach for Generating Invariant Descriptors in Visual Geolocation Tasks. Programmnaya Ingeneria, 17(4), 191-200. https://doi.org/10.17587/prin.17.191-200
Vancouver
Morozov SA, Rokhlin DE, Skorniakova EA. A Cross-Attention and Deformable Convolution Approach for Generating Invariant Descriptors in Visual Geolocation Tasks. Programmnaya Ingeneria. 2026;17(4):191-200. doi:10.17587/prin.17.191-200
BibTeX
@article{Morozov2026,
author = {Morozov, S. A. and Rokhlin, D. E. and Skorniakova, E. A.},
title = {A Cross-Attention and Deformable Convolution Approach for Generating Invariant Descriptors in Visual Geolocation Tasks},
journal = {Programmnaya Ingeneria},
year = {2026},
volume = {17},
number = {4},
pages = {191--200},
doi = {10.17587/prin.17.191-200}
}
EUVIMED