Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published October 27, 2019 | Version 1.0.0
Dataset Open

RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments

  • 1. Imperial College London

Description

The RT-BENE dataset is licensed under CC BY-NC-SA 4.0. Commercial usage is not permitted. If you use our blink estimation code or dataset, please cite the relevant paper:

@inproceedings{CortaceroICCV2019W,
author={Kevin Cortacero and Tobias Fischer and Yiannis Demiris},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision Workshops},
title = {RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments},
year = {2019},
}

More information can be found on the Personal Robotic Lab's website: https://www.imperial.ac.uk/personal-robotics/software/.

Overview

We manually annotated images that are contained in the "noglasses" part of the RT-GENE dataset with blink annotations. This dataset contains the extracted eye image patches and associated annotations.

In particular, rt_bene_subjects.csv is an overview CSV file with the following columns:

  1. id
  2. subject csv file
  3. path to left eye images
  4. path to right eye images
  5. training/validation/discarded category
  6. fold-id for the 3-fold evaluation.

Each individual "blink_labels" CSV file (s000_blink_labels.csv to s016_blink_labels.csv) contains two columns:

  1. image file name
  2. label, where 0.0 is the annotation for open eyes, 1.0 for blinks and 0.5 for annotator disagreement (these images are discarded)

Associated code

Please see the code repository for code allowing to train and evaluate a deep neural network based on the RT-BENE dataset. The code repository also links to pre-trained models and code for real-time inference.

Notes

We thank the Personal Robotics Lab members at Imperial College for their support during this research. This work was supported by the European Union H2020 Framework Programme (Project PAL, H2020-PHC-643783), and a Royal Academy of Engineering Chair in Emerging Technologies.

Files

rt_bene_subjects.csv

Files (937.0 MB)

Name Size Download all
md5:a07810daaf6d2053a9ed1f782e5f360c
1.6 kB Preview Download
md5:a2c04daa26f3d73b1b94c0a94c027755
335.6 kB Preview Download
md5:9c4591dd8eb1c6dced120f768c8acd23
98.9 MB Download
md5:e643663fe17a7def64b616b06be992ec
268.4 kB Preview Download
md5:63784833a779e48a670d183b387cc501
72.4 MB Download
md5:df2566fc9218ab81036342ce04d7f2f0
242.2 kB Preview Download
md5:4ae9f7dbd3ec23b9997bbbfa54e05f2b
69.0 MB Download
md5:4523566e1784c65fea7d57c6465f0926
86.4 kB Preview Download
md5:e5455af8d9acd1be8eb11118529b9a4e
27.5 MB Download
md5:ad56bd2935cb2fb13ae9d356db2fad2e
120.4 kB Preview Download
md5:9a31825d3446a3b25cf23160ec46be7a
34.6 MB Download
md5:540aee0018730bff5594ae8f9b3181a2
138.1 kB Preview Download
md5:691952ac7aeeddf355a390e18dc80bf4
43.2 MB Download
md5:b38f89d1ff9b83fe48eefb8e0a1169bd
192.8 kB Preview Download
md5:01145fb0bd26b2fd1ce76d1a226832da
57.1 MB Download
md5:1b62a3a2c45efbd0af3ef36900151ead
48.2 kB Preview Download
md5:7ca6f32635c4d8d70a075fd1bcd195a8
15.0 MB Download
md5:039e95cff0b54b8dab95277ed84a2815
156.6 kB Preview Download
md5:91da9e6da1075e80f60307516055ee6c
50.6 MB Download
md5:c740478ed59c9c5cf5e34144ab3ed272
107.4 kB Preview Download
md5:7aad909fc39baaa4cbc53051d7d6c89f
31.8 MB Download
md5:4f89f810193adf22ec9f990a05d42bea
423.6 kB Preview Download
md5:c17f5ce5316cc74356ec09b17b46faac
140.0 MB Download
md5:f1159a7dd8d80880074cd609b0b33cc7
329.2 kB Preview Download
md5:9a9295e571d803e138f9094a6f0331a3
114.2 MB Download
md5:7722524624f3dcf53116e7081a7de5c7
31.8 kB Preview Download
md5:e925025262025b3c6145c42b08255ba1
9.9 MB Download
md5:e220c8bccdf1b6c5a3886bfdb30a9d1f
255.7 kB Preview Download
md5:ad46bc84d80a35c57d36921f411cb5df
75.3 MB Download
md5:7b3d85a970e90ca4627f2cac39d3a1e6
137.8 kB Preview Download
md5:68c8282b56afa29fad7cfb50deb7b9cc
41.1 MB Download
md5:825af2e4609c3f1534438777fbf7c45e
55.4 kB Preview Download
md5:cc2547496bb28ed5298f11c587b67fc6
16.5 MB Download
md5:c449b5da2fee9ecc1c8cbb0f15d179f3
116.5 kB Preview Download
md5:d64f7e91f234ab3ac3ddbf19bbef427a
36.7 MB Download

Additional details

Related works

Is supplement to
Conference paper: 10044/1/74529 (Handle)

Funding

PAL – Personal Assistant for healthy Lifestyle (PAL) 643783
European Commission

References

  • K. Cortacero, T. Fischer and Y. Demiris. "RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments", ICCV 2019 Workshop on Gaze Estimation and Prediction in the Wild