Salvato in:
Dettagli Bibliografici
Autori principali: Kostiv, Markiyan, Adamovskyi, Anatolii, Cherniavskyi, Yevhen, Varenyk, Mykyta, Viniavskyi, Ostap, Krashenyi, Igor, Dobosevych, Oles
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.05229
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909677687668736
author Kostiv, Markiyan
Adamovskyi, Anatolii
Cherniavskyi, Yevhen
Varenyk, Mykyta
Viniavskyi, Ostap
Krashenyi, Igor
Dobosevych, Oles
author_facet Kostiv, Markiyan
Adamovskyi, Anatolii
Cherniavskyi, Yevhen
Varenyk, Mykyta
Viniavskyi, Ostap
Krashenyi, Igor
Dobosevych, Oles
contents Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to rapid changes in object appearance and position within the frame. The task becomes even more challenging due to image degradation caused by cloud video streaming and compression algorithms. We present how instance association learning from single-frame annotations can overcome these challenges. We show that global features of the scene provide crucial context for low-FPS instance association, allowing our solution to be robust to distractors and gaps in detections. We also demonstrate that such a tracking approach maintains high association quality even when reducing the input image resolution and latent representation size for faster inference. Finally, we present a benchmark dataset of annotated military vehicles collected from publicly available data sources. This paper was initially presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by the Information Systems Technology (IST)Scientific and Technical Committee, IST-209-RSY - the ICMCIS, held in Oeiras, Portugal, 13-14 May 2025.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05229
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
Kostiv, Markiyan
Adamovskyi, Anatolii
Cherniavskyi, Yevhen
Varenyk, Mykyta
Viniavskyi, Ostap
Krashenyi, Igor
Dobosevych, Oles
Computer Vision and Pattern Recognition
Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to rapid changes in object appearance and position within the frame. The task becomes even more challenging due to image degradation caused by cloud video streaming and compression algorithms. We present how instance association learning from single-frame annotations can overcome these challenges. We show that global features of the scene provide crucial context for low-FPS instance association, allowing our solution to be robust to distractors and gaps in detections. We also demonstrate that such a tracking approach maintains high association quality even when reducing the input image resolution and latent representation size for faster inference. Finally, we present a benchmark dataset of annotated military vehicles collected from publicly available data sources. This paper was initially presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by the Information Systems Technology (IST)Scientific and Technical Committee, IST-209-RSY - the ICMCIS, held in Oeiras, Portugal, 13-14 May 2025.
title Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.05229