Dist-Tracker: A Small Object-Aware Detector and Tracker for UAV Tracking
Bibliographic record
Abstract
The widespread adoption of civil unmanned aerial vehicles (UAVs) has accelerated the development of anti-UAV technologies. Despite thermal infrared video enables all-weather surveillance, existing methods for multi-UAV tracking struggle with low thermal contrast, object scale variation, and erratic motion patterns. In this paper, we propose Dist-Tracker, a two-stage framework integrating a Scale-Shape-Quality (SSQ) detector based on YOLOv12 and Fusion of L2-IoU Tracker (FLIT) to address these challenges. For detection, SSQ introduces scale-aware Wasserstein distance with covariance alignment, dynamic shape-aware penalties, and adaptive gradient modulation to resolve geometric instability in small infrared targets. For tracking, FLIT synergizes IoU and L2 metrics with camera motion compensation, mitigating spatial jitter and occlusion-induced ambiguities through hybrid cost metric optimization. Comprehensive evaluations on the validation set from the Anti-UAV dataset demonstrate that our proposed framework achieves remarkable performance, with a detection A P50of 93.9 % and a tracking MOTA of 77.5 % in cluttered infrared environments, significantly advancing UAV swarm detecting and tracking capabilities through geometric-stable perception and motion-resilient association. Our method won first place in the 4-th Anti-UAV challenge Track3 (tracking MOTA:81.32% on the official test set).
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".