Skip to content

Dataset · dronefreak

Annotated traffic lights for object detection in YOLO format

dronefreak/LISA-Traffic-Lights

An unofficial conversion of the LISA dataset with traffic light bounding boxes for training detectors.

What's inside

The set consists of road scene images with traffic light annotations in the form of bounding boxes. This is an unofficial repackaging of the original LISA Traffic Light Dataset by researchers from the Laboratory for Intelligent and Safe Automobiles. The data is exported to YOLO format and distributed under the CC BY-NC-SA 4.0 license.

What you can do with it

  • Training YOLO family detectors for traffic light recognition
  • Prototyping advanced driver assistance systems (ADAS) and autonomous vehicles
  • Validating small object detection models on road scenes
Tasks
Object detection
Languages
English
Size
10K–100K rows
Downloads this month
20K
Likes
4

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("dronefreak/LISA-Traffic-Lights")