Consists of 100 challenging video sequences captured from real-world traffic scenes (over 140,000 frames with rich annotations, including occlusion, weather, vehicle category, truncation, and vehicle bounding boxes) for object detection, object tracking and MOT system.
Source: UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
Image Source: UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
Variants: UA-DETRAC
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Multiple Object Tracking | EB & TADN | Transformer-based assignment decision network for … | 2022-08-06 |
| Object Detection | FFAVOD-SpotNet with U-Net | FFAVOD: Feature Fusion Architecture for … | 2021-09-15 |
| 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 | CenterNet | Objects as Points | 2019-04-16 |
| Object Detection | 3D-DETNet | 3D-DETNet: a Single Stage Video-Based … | 2018-01-05 |
| Object Detection | YOLOv2 | YOLO9000: Better, Faster, Stronger | 2016-12-25 |
| Object Detection | R-FCN | R-FCN: Object Detection via Region-based … | 2016-05-20 |
| Object Detection | Faster R-CNN | Faster R-CNN: Towards Real-Time Object … | 2015-06-04 |
Recent papers with results on this dataset: