Multi-Object Tracking in UAV Videos: A YOLOv11 Fusion Method for Detection and Segmentation Optimization
Bibliographic record
Abstract
Abstract. The rapid evolution of deep learning has significantly advanced multi-object tracking (MOT) in UAV-based remote sensing applications. However, accurately detecting and tracking objects of varying sizes in complex UAV-captured environments remains a challenge. This research introduces a novel fusion-based approach that leverages YOLOv11, a state-of-the-art object detection framework, to enhance MOT performance on the VisDrone UAV dataset. The proposed method integrates two YOLOv11 configurations: detection mode, paired with the Bot-SORT tracker, optimized for large objects to ensure high precision and localization accuracy, and segmentation mode, combined with the Byte-Track tracker, designed to effectively detect and track smaller, less prominent objects. By fusing the outputs of these configurations, the approach ensures comprehensive object coverage across different size ranges, thereby improving both detection and tracking accuracy while enhancing segmentation performance. This method addresses critical limitations in existing models, such as low recall for small objects and imprecise localization for larger ones, which are particularly challenging in UAV datasets due to varying altitudes, occlusions, and dynamic backgrounds. The fusion strategy employs Intersection over Union (IoU)-based matching, weighted bounding box fusion, and confidence thresholding to enhance tracking reliability and accuracy. Experimental evaluations on the VisDrone dataset, using motion tracking metrics and the F1 score for detection and segmentation, demonstrate significant performance improvements across multiple UAV videos. The results show that the fused approach outperforms individual configurations while maintaining consistent object identity tracking over time. This research contributes to UAV-based remote sensing by providing a scalable and efficient MOT framework, making it particularly valuable for applications such as surveillance, traffic monitoring, and disaster response, where precise object localization and tracking are crucial.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".