TY - JOUR

T1 - Visual place recognition for aerial imagery: A survey

AU - Moskalenko, I.

AU - Kornilova, A.

AU - Ferrer, G.

N1 - Export Date: 4 November 2024 CODEN: RASOE

PY - 2025/1

Y1 - 2025/1

N2 - Aerial imagery and its direct application to visual localization is an essential problem for many Robotics and Computer Vision tasks. While Global Navigation Satellite Systems (GNSS) are the standard default solution for solving the aerial localization problem, it is subject to a number of limitations, such as, signal instability or solution unreliability that make this option not so desirable. Consequently, visual geolocalization is emerging as a viable alternative. However, adapting Visual Place Recognition (VPR) task to aerial imagery presents significant challenges, including weather variations and repetitive patterns. Current VPR reviews largely neglect the specific context of aerial data. This paper introduces a methodology tailored for evaluating VPR techniques specifically in the domain of aerial imagery, providing a comprehensive assessment of various methods and their performance. However, we not only compare various VPR methods, but also demonstrate the importance of selecting appropriate zoom and overlap levels when constructing map tiles to achieve maximum efficiency of VPR algorithms in the case of aerial imagery. The code is available on our GitHub repository — https://github.com/prime-slam/aero-vloc. © 2024 Elsevier B.V.

AB - Aerial imagery and its direct application to visual localization is an essential problem for many Robotics and Computer Vision tasks. While Global Navigation Satellite Systems (GNSS) are the standard default solution for solving the aerial localization problem, it is subject to a number of limitations, such as, signal instability or solution unreliability that make this option not so desirable. Consequently, visual geolocalization is emerging as a viable alternative. However, adapting Visual Place Recognition (VPR) task to aerial imagery presents significant challenges, including weather variations and repetitive patterns. Current VPR reviews largely neglect the specific context of aerial data. This paper introduces a methodology tailored for evaluating VPR techniques specifically in the domain of aerial imagery, providing a comprehensive assessment of various methods and their performance. However, we not only compare various VPR methods, but also demonstrate the importance of selecting appropriate zoom and overlap levels when constructing map tiles to achieve maximum efficiency of VPR algorithms in the case of aerial imagery. The code is available on our GitHub repository — https://github.com/prime-slam/aero-vloc. © 2024 Elsevier B.V.

KW - Aerial imagery

KW - Benchmark

KW - Geolocalization

KW - Visual place recognition

KW - Global positioning system

KW - Image coding

KW - Essential problems

KW - Geo-localisation

KW - Global Navigation Satellite Systems

KW - Localization problems

KW - Place recognition

KW - Signal instabilities

KW - Visual localization

KW - Aerial photography

U2 - 10.1016/j.robot.2024.104837

DO - 10.1016/j.robot.2024.104837

M3 - статья

VL - 183

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

M1 - 104837

ER -