Unmanned Aerial Vehicle Benchmark Object Detection and Tracking
UAVDT is a large scale challenging UAV Detection and Tracking benchmark (i.e., about 80, 000 representative frames from 10 hours raw videos) for 3 important fundamental tasks, i.e., object DETection
(DET), Single Object Tracking (SOT) and Multiple Object Tracking (MOT).
The dataset is captured by UAVs in various complex scenarios. The objects of
interest in this benchmark are vehicles. The frames are manually annotated with bounding boxes and some useful attributes, e.g., vehicle category and occlusion.
The UAVDT benchmark consists of 100 video sequences, which are selected
from over 10 hours of videos taken with an UAV platform at a number of locations in urban areas, representing various common scenes including squares, arterial streets, toll stations, highways, crossings and T-junctions. The videos
are recorded at 30 frames per seconds (fps), with the JPEG image resolution of 1080 × 540 pixels.
Variants: UAVDT
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Multi-Object Tracking | SAM2MOT | SAM2MOT: A Novel Paradigm of … | 2025-04-06 |
| Multi-Object Tracking | DroneMOT | DroneMOT: Drone-based Multi-Object Tracking Considering … | 2024-07-12 |
| Object Detection | FFAVOD-SpotNet with U-Net | FFAVOD: Feature Fusion Architecture for … | 2021-09-15 |
| Object Detection | PRB-FPN | Parallel Residual Bi-Fusion Feature Pyramid … | 2020-12-03 |
| Object Detection | RN-VID | RN-VID: A Feature Fusion Architecture … | 2020-03-24 |
| Object Detection | SpotNet | SpotNet: Self-Attention Multi-Task Network for … | 2020-02-13 |
| Object Detection | R-FCN | The Unmanned Aerial Vehicle Benchmark: … | 2018-03-26 |
| Object Detection | SSD | The Unmanned Aerial Vehicle Benchmark: … | 2018-03-26 |
| Object Detection | Faster-RCNN | The Unmanned Aerial Vehicle Benchmark: … | 2018-03-26 |
| Object Detection | RON | The Unmanned Aerial Vehicle Benchmark: … | 2018-03-26 |
Recent papers with results on this dataset: