E-VLC Dataset

home

We present the E-VLC dataset for Visible Light Communication (VLC) that consists of:

precisely synchronized events, frames, ground-truth pose of LED markers and cameras.
bounding-box annotations for LEDs.
various recording conditions (motion type, scene luminance, event camera sensitivity) to cover real-world applications.

News

April. 28, 2025	The dataset paper is published on arxiv. Link
April. 3, 2025	E-VLC dataset webpage is released!

BibTeX

Please cite the following publication when using this benchmark in an academic context:

    
@InProceedings{Shiba25cvprw,
  author = {Shiba, Shintaro and Kong, Quan and Kobori, Norimasa},
  title = {E-VLC: A Real-World Dataset for Event-based Visible Light Communication And Localization},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  year = {2025}
}

Abs arXiv Github

Optical communication using modulated LEDs (e.g., visible light communication) is an emerging application for event cameras, thanks to their high spatio-temporal resolutions. Event cameras can be used simply to decode the LED signals and also to localize the camera relative to the LED marker positions. However, there is no public dataset to benchmark the decoding and localization in various real-world settings. We present, to the best of our knowledge, the first public dataset that consists of an event camera, a frame camera, and ground-truth poses that are precisely synchronized with hardware triggers. It provides various camera motions with various sensitivities in different scene brightness settings, both indoor and outdoor. Furthermore, we propose a novel method of localization that leverages the Contrast Maximization framework for motion estimation and compensation. The detailed analysis and experimental results demonstrate the advantages of LED-based localization with events over the conventional AR-marker–based one with frames, as well as the efficacy of the proposed method in localization. We hope that the proposed dataset serves as a future benchmark for both motion-related classical computer vision tasks and LED marker decoding tasks simultaneously, paving the way to broadening applications of event cameras on mobile devices.

Term of Use

Subject to the user's compliance with this Terms of Use, users may access, copy, use, modify, and disclose this dataset (hereinafter E-VLC Dataset”) only for academic research purposes (hereinafter “Usage License”). Any direct or indirect commercial use of this E-VLC Dataset under this Usage License is NOT allowed. By downloading E-VLC Dataset, users shall be deemed to have agreed to the term of use.
The disclosure of this E-VLC Dataset in your research is only allowed for demonstration in academic publications and presentations. The original property holder‘s name (Woven by Toyota, Inc.) of this E-VLC Dataset is necessary to be indicated in your publications or presentations.
Any distribution of this E-VLC Dataset whether in its original form, modified, or combined with another dataset is NOT allowed.
Woven by Toyota, Inc. shall not be liable to users for any losses, expenses, and damages caused by using this E-VLC Dataset. All users agree to indemnify, defend, and hold harmless any individuals who participated in the data collection and Woven by Toyota, Inc., and its officers, employees, and agents, individually and collectively.
Any use that is not in line with the above terms will cancel the Usage License and users should permanently remove the E-VLC Dataset and any derivative works of the E-VLC Dataset from their environment.