RadarFoot: Fine-grain Ground Surface Context Awareness for Smart Shoes

要旨

Everyday, billions of people use footwear for walking, running, or exercise. Of emerging interest are ``smart footwear'', which help users track gait, count steps or even analyse performance. However, such nascent footwear lack fine-grain ground surface context awareness, which could allow them to adapt to the conditions and create usable functions and experiences. Hence, this research aims to recognize the walking surface using a radar sensor embedded in a shoe, enabling ground context-awareness. Using data collected from 23 participants from an in-the-wild setting, we developed several classification models. We show that our model can detect five common terrain types with an accuracy of 80.0\% and further ten terrain types with an accuracy of 66.3\%, while moving. Importantly, it can detect the gait motion types such as `walking', `stepping up', `stepping down', `still', with an accuracy of 90\%. Finally, we present potential use cases and insights for future work based on such ground-aware smart shoes.

著者
Don Samitha Elvitigala
Monash University, Melbourne, Victoria, Australia
Yunfan Wang
UNSW, Sydney, Austria
Yongquan Hu
University of New South Wales, Sydney, Australia
Aaron J. Quigley
CSIRO’s Data61 , Sydney, NSW, Australia
論文URL

https://doi.org/10.1145/3586183.3606738

動画

会議: UIST 2023

ACM Symposium on User Interface Software and Technology

セッション: Sensory Shenanigans: Immersion and Illusions in Mixed Reality

Venetian Room
6 件の発表
2023-11-01 18:00:00
2023-11-01 19:20:00