Ciliberto, Mathias, Ponce Cuspinera, Luis and Roggen, Daniel (2017) Complex human gestures encoding from wearable inertial sensors for activity recognition. International Conference on Embedded Wireless Systems and Networks, Madrid, Spain, February 14-16, 2018. Published in: Giustiniano, Domenico and Koutsonikolas, Dimitrios, (eds.) International Conference on Embedded Wireless Systems and Networks. ACM (Accepted)

PDF - Accepted Version Restricted to SRO admin only Download (351kB)

Abstract

We demonstrate a method to encode complex human gestures acquired from inertial sensors for activity recognition. Gestures are encoded as a stream of symbols which represent the change in orientation and displacement of the body limbs over time.
The first novelty of this encoding is to enable the reuse previously developed single-channel template matching algorithms also when multiple sensors are used simultaneously.
The second novelty is to encode changes in orientation of limbs which is important in some activities, such as sport analytics.
We demonstrate the method using our custom inertial platform, BlueSense. Using a set of five BlueSense nodes, we implemented a motion tracking system that displays a 3D human model and shows in real-time the corresponding movement encoding.

Item Type:	Conference Proceedings
Keywords:	Wearable computing; activity recognition; motion encoding; motion tracking; motion sensing; IMU; BlueSense
Schools and Departments:	School of Engineering and Informatics > Engineering and Design
Research Centres and Groups:	Sensor Technology Research Centre
Subjects:	Q Science > Q Science (General) > Q0300 Cybernetics T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics > TK7885 Computer engineering. Computer hardware
Depositing User:	Daniel Roggen
Date Deposited:	02 Jan 2018 09:25
Last Modified:	08 Jan 2018 13:40
URI:	http://sro.sussex.ac.uk/id/eprint/72420

View download statistics for this item

📧 Request an update