Electric Vehicle Charging Stations Dataset

Objective: Evaluation and Development of Approaches for EVCS Detection
EVCS Dataset: Dataset with high quality, fine-grained annotations of electric vehicle charging station

• Motivation
  • Electric vehicles are becoming more common
  • Automatic detection of charging stations helps in automated/assisted parking applications
  • Existing image datasets for driving scenarios do not include annotated charging stations
• Dataset contains
  • Part A: Fine-grained instance mask annotations of 8 common charging station types
  • Part B: 759 images, covering 13 additional types of EVCS labelled at supercategory level
• Demonstration Video [YouTube]
• If you use the data, please cite our paper [1]

Version 1.0

Dataset

Download dataset images

• EVCS Dataset - Part A
• EVCS Dataset - Part B

Details about the EVCS dataset and how to train and test the baseline detectors as presented in our paper [1] are explained in this guide

• Evaluation scripts at GitHub

Reference:

[1] Lin Chen, Sönke Südbeck, Christoph Riggers, Tobias Geib, Kai Cordes, and Hellward Broszio:
"EVCS: A Benchmark for Fine-Grained Electric Vehicle Charging Station Detection", GCPR 2025, Lecture Notes in Computer Science, vol 16125. Springer, pp 73–88, https://doi.org/10.1007/978-3-032-12840-9_6

EVCS Dataset by VISCODA GmbH is licensed under CC BY-NC-SA 4.0.