Robust Ultra-Lightweight Multi-Object Tracking on UAVs in Diverse Weather Environments
Bibliographic record
Abstract
The integration of unmanned aerial vehicles (UAVs) into intelligent transportation systems (ITS) provides a scalable and dynamic solution for real-time traffic monitoring and multi-object tracking (MOT). This paper presents a comprehensive evaluation of lightweight and resilient MOT algorithms optimized for UAV platforms operating under constrained computational budgets and diverse weather conditions. Using the UAVDT dataset, which features complex urban environments with occlusions, varying illumination, and small object instances, we assess three advanced MOT frameworks: FairMOT with YOLOv5 and HRNet18 backbones, and ByteTrack with a YOLOX-S backbone. The proposed FairMOT-YOLOv5 configuration consistently outperforms existing state-of-the-art methods in terms of identity preservation, tracking robustness, and deployment feasibility. It achieves optimal performance using a single NVIDIA RTX 3080 GPU with 10GB VRAM, marking the best results we have attained under the given constraints. While the HRNet18 backbone yields slightly higher detection precision, it does so with significantly increased training time. ByteTrack underperforms in recall and stability under complex conditions. These findings reinforce the effectiveness of unified detection and re-identification frameworks in aerial tracking and demonstrate the practical readiness of our approach for real-world ITS applications across diverse and adverse weather conditions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".