german-traffic-sign-detection
收藏魔搭社区2026-01-09 更新2025-11-03 收录
下载链接:
https://modelscope.cn/datasets/keremberke/german-traffic-sign-detection
下载链接
链接失效反馈官方服务:
资源简介:
<div align="center">
<img width="640" alt="keremberke/german-traffic-sign-detection" src="https://huggingface.co/datasets/keremberke/german-traffic-sign-detection/resolve/main/thumbnail.jpg">
</div>
### Dataset Labels
```
['animals', 'construction', 'cycles crossing', 'danger', 'no entry', 'pedestrian crossing', 'school crossing', 'snow', 'stop', 'bend', 'bend left', 'bend right', 'give way', 'go left', 'go left or straight', 'go right', 'go right or straight', 'go straight', 'keep left', 'keep right', 'no overtaking', 'no overtaking -trucks-', 'no traffic both ways', 'no trucks', 'priority at next intersection', 'priority road', 'restriction ends', 'restriction ends -overtaking -trucks--', 'restriction ends -overtaking-', 'restriction ends 80', 'road narrows', 'roundabout', 'slippery road', 'speed limit 100', 'speed limit 120', 'speed limit 20', 'speed limit 30', 'speed limit 50', 'speed limit 60', 'speed limit 70', 'speed limit 80', 'traffic signal', 'uneven road']
```
### Number of Images
```json
{'test': 54, 'valid': 108, 'train': 383}
```
### How to Use
- Install [datasets](https://pypi.org/project/datasets/):
```bash
pip install datasets
```
- Load the dataset:
```python
from datasets import load_dataset
ds = load_dataset("keremberke/german-traffic-sign-detection", name="full")
example = ds['train'][0]
```
### Roboflow Dataset Page
[https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1](https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1?ref=roboflow2huggingface)
### Citation
```
@misc{ gtsdb---german-traffic-sign-detection-benchmark_dataset,
title = { GTSDB - German Traffic Sign Detection Benchmark Dataset },
type = { Open Source Dataset },
author = { Mohamed Traore },
howpublished = { \\url{ https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark } },
url = { https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { jul },
note = { visited on 2023-01-16 },
}
```
### License
CC BY 4.0
### Dataset Summary
This dataset was exported via roboflow.com on January 16, 2023 at 9:04 PM GMT
Roboflow is an end-to-end computer vision platform that helps you
* collaborate with your team on computer vision projects
* collect & organize images
* understand and search unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time
For state of the art Computer Vision training notebooks you can use with this dataset,
visit https://github.com/roboflow/notebooks
To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
The dataset includes 545 images.
Signs are annotated in COCO format.
The following pre-processing was applied to each image:
* Auto-orientation of pixel data (with EXIF-orientation stripping)
No image augmentation techniques were applied.
<div align="center"><img width="640" alt="keremberke/german-traffic-sign-detection" src="https://huggingface.co/datasets/keremberke/german-traffic-sign-detection/resolve/main/thumbnail.jpg"></div>
### 数据集标签
['注意动物(animals)', '施工警示(construction)', '注意非机动车横穿(cycles crossing)', '通用危险警示(danger)', '禁止驶入(no entry)', '人行横道预告(pedestrian crossing)', '学生过街警示(school crossing)', '积雪易滑警示(snow)', '停车让行(stop)', '连续弯路(bend)', '向左急转弯(bend left)', '向右急转弯(bend right)', '减速让行(give way)', '只准左转(go left)', '只准左转或直行(go left or straight)', '只准右转(go right)', '只准右转或直行(go right or straight)', '只准直行(go straight)', '靠左行驶(keep left)', '靠右行驶(keep right)', '禁止超车(no overtaking)', '禁止货车超车(no overtaking -trucks-)', '双向禁止通行(no traffic both ways)', '禁止货车通行(no trucks)', '前方路口优先通行(priority at next intersection)', '优先通行道路(priority road)', '限制解除(restriction ends)', '禁止货车超车限制解除(restriction ends -overtaking -trucks--)', '禁止超车限制解除(restriction ends -overtaking-)', '限速80km/h解除(restriction ends 80)', '道路变窄(road narrows)', '环岛行驶(roundabout)', '路面湿滑(slippery road)', '限速100km/h(speed limit 100)', '限速120km/h(speed limit 120)', '限速20km/h(speed limit 20)', '限速30km/h(speed limit 30)', '限速50km/h(speed limit 50)', '限速60km/h(speed limit 60)', '限速70km/h(speed limit 70)', '限速80km/h(speed limit 80)', '前方交通信号灯警示(traffic signal)', '路面不平警示(uneven road)']
### 图像数量
json
{'测试集': 54, '验证集': 108, '训练集': 383}
### 使用方法
- 安装数据集(datasets)库:
bash
pip install datasets
- 加载数据集:
python
from datasets import load_dataset
ds = load_dataset("keremberke/german-traffic-sign-detection", name="full")
example = ds['train'][0]
### Roboflow 数据集页面
[https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1](https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1?ref=roboflow2huggingface)
### 引用
@misc{ gtsdb---german-traffic-sign-detection-benchmark_dataset,
title = { GTSDB——德国交通标志检测基准数据集 },
type = { 开源数据集 },
author = { Mohamed Traore },
howpublished = { \url{ https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark } },
url = { https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { jul },
note = { 访问日期:2023-01-16 },
}
### 许可证
知识共享署名4.0国际许可协议(CC BY 4.0)
### 数据集概述
本数据集于2023年1月16日格林尼治标准时间21:04通过roboflow.com导出。
Roboflow是一款端到端计算机视觉平台,可协助您完成以下工作:
* 与团队协作开展计算机视觉项目
* 收集并整理图像数据
* 理解并检索非结构化图像信息
* 进行标注并构建数据集
* 导出、训练并部署计算机视觉模型
* 使用主动学习技术随时间迭代优化数据集
如需可用于本数据集的顶尖计算机视觉训练笔记,请访问 https://github.com/roboflow/notebooks
如需查找超过10万个其他数据集与预训练模型,请访问 https://universe.roboflow.com
本数据集共包含545张图像,交通标志以COCO格式进行标注。
已对每张图像应用以下预处理操作:
* 像素数据自动校正方向(剥离EXIF方向元数据)
未应用任何图像增强技术。
提供机构:
maas
创建时间:
2025-10-03



