Traffic Signs Detection Europe Computer Vision Project
Updated 4 months ago
0
views0
downloads
Dataset structure
The dataset contains 55 classes of unique traffic signs. There are 4 main categories:
- forb
- info
- mand
- warn
Each class has one of these prefixes in it's name indicating the category of the traffic sign: forbidden, informational, mandatorry and warning, respectively.
Each image is of size 640x640px. If a traffic sign was recognizable it was labeled but if I could barely tell what the sign was it was not labeled, no matter the distance to the traffic sign. The dataset is not perfectly balanced due to the frequency of traffic signs. Naturally some signs appear more than others. There are some images with no labels, those were collected when models would get false positive detections.
Data collection
Most of the images were collected from Google Maps, Romania, and manually labeled. There's a small part of images that were automatically collected from YouTube videos, by a trained model, and then manually checked (around 150).
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
traffic-signs-detection-europe-gtfwu_dataset,
title = { Traffic Signs Detection Europe Dataset },
type = { Open Source Dataset },
author = { jaber },
howpublished = { \url{ https://universe.roboflow.com/jaber-3enyd/traffic-signs-detection-europe-gtfwu } },
url = { https://universe.roboflow.com/jaber-3enyd/traffic-signs-detection-europe-gtfwu },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { aug },
note = { visited on 2024-12-22 },
}