MOT15

displayName: MOT15
labelTypes:
- Box2D_tracking
- Box3D Tracking
license:
- CC BY-NC-SA 3.0
mediaTypes:
- Video
paperUrl: ""
publishDate: "2015"
publishUrl: https://motchallenge.net/data/MOT15/
publisher:
- ETH Zurich
- University of Adelaide
- Technical University of Darmstadt
tags:
- Square
- Mall
- road
- Garden
- Human
taskTypes:
- Object Tracking

---
# 数据集介绍
## 简介
该基准包含在不受约束的环境中使用静态和移动摄像机拍摄的视频序列。跟踪和评估是在图像坐标中完成的。
## 类定义
```
pedestrian
```
## 引文
```
@article{leal2015motchallenge,
title={Motchallenge 2015: Towards a benchmark for multi-target tracking},
author={Leal-Taix{\'e}, Laura and Milan, Anton and Reid, Ian and Roth, Stefan and Schindler, Konrad},
journal={arXiv preprint arXiv:1504.01942},
year={2015}
}
```

## Download dataset
:modelscope-code[]{type="git"}