Traffic Lights of New York (TLoNY): Models
A comprehensive object detection dataset for fine-grained classification of traffic lights in New York City. The dataset includes both vehicular and pedestrian traffic signals with detailed color state annotations.
Overview
TLoNY provides accurately labeled traffic light data suitable for training object detection models, sourced from publicly available images from Unsplash. The dataset captures various lighting conditions, weather scenarios, and urban environments of New York City.
Metrics
Model Name | Recall | mAP50 | mAP50-95 |
---|---|---|---|
yolov8x-p2 | 0.50405 | 0.56544 | 0.30823 |
yolov8n | 0.43263 | 0.50172 | 0.27866 |
Download
Dataset
Models
Cite
@misc {mehmet_kerem_turkcan_2025,
author = { {Mehmet Kerem Turkcan} },
title = { traffic-lights-of-new-york (Revision 2999230) },
year = 2025,
url = { https://huggingface.co/datasets/mehmetkeremturkcan/traffic-lights-of-new-york },
doi = { 10.57967/hf/4331 },
publisher = { Hugging Face }
}
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.