Research Article
Fingertip Air-Writing with Ambient Light
@INPROCEEDINGS{10.1007/978-3-031-63992-0_11, author={Hao Liu and Hanting Ye and Xiangxie Zhang and Jie Yang and Qing Wang}, title={Fingertip Air-Writing with Ambient Light}, proceedings={Mobile and Ubiquitous Systems: Computing, Networking and Services. 20th EAI International Conference, MobiQuitous 2023, Melbourne, VIC, Australia, November 14--17, 2023, Proceedings, Part II}, proceedings_a={MOBIQUITOUS PART 2}, year={2024}, month={7}, keywords={Air-writing Ambient light Embedded AI}, doi={10.1007/978-3-031-63992-0_11} }- Hao Liu
Hanting Ye
Xiangxie Zhang
Jie Yang
Qing Wang
Year: 2024
Fingertip Air-Writing with Ambient Light
MOBIQUITOUS PART 2
Springer
DOI: 10.1007/978-3-031-63992-0_11
Abstract
Contact-free interaction with public devices could become popular. To achieve this purpose, state-of-the-art methods mainly use cameras to capture mid-air hand gestures, which are power-hungry and can raise privacy issues. In this work, we designLightDigit, a system for fingertip air-writing of digits with ambient light and photodiodes, to enable contact-free interactions with public devices. The key enabler is detecting and interpreting dynamic shadows on photodiodes introduced by fingertip movements. We design an embedded deep learning modelLightConvRNN–customized ConvRNN with attention pooling– to capture spatial and temporal patterns in the dynamic shadows. We evaluate LightDigit through extensive experiments under different light conditions. Evaluation results show that our model can achieve an accuracy of up to 98%. Through model compression, the model size is reduced by 92% with less than a 5% drop in the performance. LightDigit is robust to ambient light positions (60(^\circ )) and ambient light intensity (5000 lx).
