Foot position as indicator of spatial interest at public displays

Authors:
Bernd Huber
Affiliations:
Korea Institute of Science and Technology (KIST), Seoul, Republic of Korea
Venue:
CHI '13 Extended Abstracts on Human Factors in Computing Systems
Year:
2013

Citing 7
Cited 0

Vision-Based Face Tracking System for Large Displays

UbiComp '02 Proceedings of the 4th international conference on Ubiquitous Computing
Interactive public ambient displays: transitioning from implicit to explicit, public to personal, interaction with multiple users

Proceedings of the 17th annual ACM symposium on User interface software and technology
Human-Computer Interaction (3rd Edition)

Human-Computer Interaction (3rd Edition)
It's Mine, Don't Touch!: interactions at a large multi-touch display in a city centre

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Overcoming Assumptions and Uncovering Practices: When Does the Public Really Look at Public Displays?

Pervasive '08 Proceedings of the 6th International Conference on Pervasive Computing
Multitoe: high-precision interaction with back-projected floors based on high-resolution multi-touch input

UIST '10 Proceedings of the 23nd annual ACM symposium on User interface software and technology
Medusa: a proximity-aware multi-touch tabletop

Proceedings of the 24th annual ACM symposium on User interface software and technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motivated by and grounded in observations of foot patterns in a human-human dialogue, this study explores expressions of spatial interest through feet at public displays. We conducted an observation and recorded user foot orientation and position in a public information display environment leading to data about 84 interaction sessions. Our observations show that characteristic foot patterns can be matched with two user intentions: (A) Users who seek access to specific information, and (B) users who don't seek specific information. With the goal to detect intention through foot patterns, we classified characteristic foot patterns with a SVM pattern recognition algorithm, which resulted in a detection accuracy of 84.4%. This work can be valuable for researchers designing context-aware public displays.