Dist-Tracker: A Small Object-Aware Detector and Tracker for UAV Tracking
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
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 P<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</inf> of 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.
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 | 0.000 |
| 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) | 0.000 | 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 it