# Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage

arXiv: https://arxiv.org/abs/2507.05229 · HTML: https://mlsanity.com/paper/2507.05229/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Quasi-Dense Similarity Learning for Multiple Object Tracking](https://mlsanity.com/paper/2006.06664/) (2020)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything](https://mlsanity.com/paper/2304.06022/) (2023)
- [Self-Supervised Multi-Object Tracking with Path Consistency](https://mlsanity.com/paper/2404.05136/) (2024)
- [Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking](https://mlsanity.com/paper/2308.05911/) (2023)
- [Adapting the Segment Anything Model During Usage in Novel Situations](https://mlsanity.com/paper/2404.08421/) (2024)
- [Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Driving](https://mlsanity.com/paper/2408.09839/) (2024)

## Abstract (arXiv)

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.