# Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions

arXiv: https://arxiv.org/abs/2603.05970 · HTML: https://mlsanity.com/paper/2603.05970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification](https://mlsanity.com/paper/2302.11813/) (2023)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking](https://mlsanity.com/paper/1511.04136/) (2015)
- [DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction](https://mlsanity.com/paper/2403.02075/) (2024)
- [Unsupervised Domain Adaptation for Nighttime Aerial Tracking](https://mlsanity.com/paper/2203.10541/) (2022)
- [Self-Supervised Multi-Object Tracking with Path Consistency](https://mlsanity.com/paper/2404.05136/) (2024)
- [BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision](https://mlsanity.com/paper/2402.04519/) (2024)
- [Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns](https://mlsanity.com/paper/1803.07293/) (2018)
- [In Pursuit of Many: A Review of Modern Multiple Object Tracking Systems](https://mlsanity.com/paper/2209.04796/) (2022)
- [Uncertainty-aware Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2307.15409/) (2023)
- [Vision-Based Anti Unmanned Aerial Technology: Opportunities and Challenges](https://mlsanity.com/paper/2507.10006/) (2025)
- [MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results](https://mlsanity.com/paper/2507.12832/) (2025)

## Abstract (arXiv)

The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at link.