Wildtrack is a large-scale and high-resolution dataset. It has been captured with seven static cameras in a public open area, and unscripted dense groups of pedestrians standing and walking. Together with the camera frames, we provide an accurate joint (extrinsic and intrinsic) calibration, as well as 7 series of 400 annotated
frames for detection at a rate of 2 frames per second. This results in over 40 000 bounding boxes delimiting every person present in the area of interest, for a total of more than
300 individuals.
Variants: Wildtrack
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Multi-Object Tracking | MCBLT | MCBLT: Multi-Camera Multi-Object 3D Tracking … | 2024-12-01 |
| Multi-Object Tracking | TrackTacular (Bilinear Sampling) | Lifting Multi-View Detection and Tracking … | 2024-03-19 |
| Multi-Object Tracking | EarlyBird | EarlyBird: Early-Fusion for Multi-View Tracking … | 2023-10-20 |
| Multi-Object Tracking | ReST | ReST: A Reconfigurable Spatial-Temporal Graph … | 2023-08-25 |
| Multi-Object Tracking | MVFlow | Multi-view Tracking Using Weakly Supervised … | 2022-10-19 |
| Multi-Object Tracking | DMCT Stack | Real-time 3D Deep Multi-Camera Tracking | 2020-03-26 |
| Multi-Object Tracking | DMCT | Real-time 3D Deep Multi-Camera Tracking | 2020-03-26 |
| Multi-Object Tracking | GLMB-YOLOv3 | A Bayesian Filter for Multi-view … | 2020-01-13 |
| Multi-Object Tracking | GLMB-DO | A Bayesian Filter for Multi-view … | 2020-01-13 |
Recent papers with results on this dataset: