Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition

要旨

Millimeter wave (mmWave) Doppler radar is a new and promising sensing approach for human activity recognition, offering signal richness approaching that of microphones and cameras, but without many of the privacy-invading downsides. However, unlike audio and computer vision approaches that can draw from huge libraries of videos for training deep learning models, Doppler radar has no existing large datasets, holding back this otherwise promising sensing modality. In response, we set out to create a software pipeline that converts videos of human activities into realistic, synthetic Doppler radar data. We show how this cross-domain translation can be successful through a series of experimental results. Overall, we believe our approach is an important stepping stone towards significantly reducing the burden of training such as human sensing systems, and could help bootstrap uses in human-computer interaction.

著者
Karan Ahuja
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Yue Jiang
Max Planck Institute for Informatics, Saarbrücken, Germany
Mayank Goel
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
Chris Harrison
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States
DOI

10.1145/3411764.3445138

論文URL

https://doi.org/10.1145/3411764.3445138

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Computational Physical Interaction

[A] Paper Room 02, 2021-05-10 17:00:00~2021-05-10 19:00:00 / [B] Paper Room 02, 2021-05-11 01:00:00~2021-05-11 03:00:00 / [C] Paper Room 02, 2021-05-11 09:00:00~2021-05-11 11:00:00
Paper Room 02
12 件の発表
2021-05-10 17:00:00
2021-05-10 19:00:00
日本語まとめ
読み込み中…