SmartBuckle: human activity recognition using a 3-axis accelerometer and a wearable camera

Authors:
Yongwon Cho;Yunyoung Nam;Yoo-Joo Choi;We-Duke Cho
Affiliations:
Ajou University, Suwon, Korea;Ajou University, Suwon, Korea;Seoul University of Venture and Information, Seoul, Korea;Ajou University, Suwon, Korea
Venue:
Proceedings of the 2nd International Workshop on Systems and Networking Support for Health Care and Assisted Living Environments
Year:
2008

Citing 1
Cited 4

Performance of optical flow techniques

International Journal of Computer Vision

Tracking system based on accelerometry for users with restricted physical activity

IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part II
Activity recognition using cell phone accelerometers

ACM SIGKDD Explorations Newsletter
Semi-supervised fall detection algorithm using fall indicators in smartphone

Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication
Physical activity recognition using a single triaxial accelerometer and a barometric sensor for baby and child care in a home environment

Journal of Ambient Intelligence and Smart Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognizing human activity is one of the most important concerns in many ubiquitous computing systems. In this paper, we present a wearable intelligence device for medical monitoring applications. We called the SmartBuckle that is designed to recognize human activity and to monitor vitality. We developed human activity recognition algorithms and evaluated them by using data acquired from a 3-axis accelerometer with embedded one image sensor in a belt. In order to evaluate, acceleration data was collected from 9 activity labels. In the image sensor, we extracted activity features based on grid-based optical flow method. In the 3-axis accelerometer sensor, we used the correlation between axes and the magnitude of the FFT for feature extraction. In the experiments, our classifiers showed the excellent performance in recognizing activities with an overall accuracy rate of 93%.