Real-Time Sign Language Detection Using Human Pose Estimation

Abstract

We propose a lightweight real-time sign language detection model, as we identify the need for such a case in videoconferencing. We extract optical flow features based on human pose estimation and, using a linear classifier, show these features are meaningful with an accuracy of 80%, evaluated on the DGS Corpus. Using a recurrent model directly on the input, we see improvements of up to 91% accuracy, while still working under 4ms. We describe a demo application to sign language detection in the browser in order to demonstrate its usage possibility in videoconferencing applications.

Cite

Text

Moryossef et al. "Real-Time Sign Language Detection Using Human Pose Estimation." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-66096-3_17

Markdown

[Moryossef et al. "Real-Time Sign Language Detection Using Human Pose Estimation." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/moryossef2020eccvw-realtime/) doi:10.1007/978-3-030-66096-3_17

BibTeX

@inproceedings{moryossef2020eccvw-realtime,
  title     = {{Real-Time Sign Language Detection Using Human Pose Estimation}},
  author    = {Moryossef, Amit and Tsochantaridis, Ioannis and Aharoni, Roee and Ebling, Sarah and Narayanan, Srini},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {237-248},
  doi       = {10.1007/978-3-030-66096-3_17},
  url       = {https://mlanthology.org/eccvw/2020/moryossef2020eccvw-realtime/}
}