Sensing Fine-Grained Hand Activity with Smartwatches

Capturing fine-grained hand activity could make computational experiences more powerful and contextually aware. Indeed, philosopher Immanuel Kant argued, "the hand is the visible part of the brain." However, most prior work has focused on detecting whole-body activities, such as walking, running and bicycling. In this work, we explore the feasibility of sensing hand activities from commodity smartwatches, which are the most practical vehicle for achieving this vision. Our investigations started with a 50 participant, in-the-wild study, which captured hand activity labels over nearly 1000 worn hours. We then studied this data to scope our research goals and inform our technical approach. We conclude with a second, in-lab study that evaluates our classification stack, demonstrating 95.2% accuracy across 25 hand activities. Our work highlights an underutilized, yet highly complementary contextual channel that could unlock a wide range of promising applications.



Research Team: Gierad Laput and Chris Harrison

Citation

Laput, G. and Harrison, C. 2019. Sensing Fine-Grained Hand Activity with Smartwatches. In Proceedings of the 37th Annual SIGCHI Conference on Human Factors in Computing Systems (Glasgow, UK, May 4 - 9, 2019). CHI '19. ACM, New York, NY. Paper 338, 13 pages.

Additional Media

Other than the paper PDF, all media on this page is shared under Creative Commons BY 3.0