TY - GEN
T1 - A fall detection system using low resolution infrared array sensor
AU - Mashiyama, Shota
AU - Hong, Jihoon
AU - Ohtsuki, Tomoaki
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/6/25
Y1 - 2014/6/25
N2 - Nowadays, aging society is a big problem and demand for monitoring systems is becoming higher. Under this circumstance, a fall is a main factor of accidents at home. From this point of view, we need to detect falls expeditiously and correctly. However, usual methods like using a video camera or a wearable device have some issues in privacy and convenience. In this paper, we propose a system of fall detection using a low resolution infrared array sensor. The proposed system uses this sensor with advantages of privacy protection (low resolution), low cost (cheap sensor), and convenience (small device). We propose four features and based on them, classify activities as either a fall or a non-fall using k-nearest neighbor (k-NN) algorithm. We show a proof-of-concept of our proposed system using a commercial-off-the-shelf (COTS) hardware. Results of experiments show the detection rate of higher than 94 % irrespective of training data contains object's data or not.
AB - Nowadays, aging society is a big problem and demand for monitoring systems is becoming higher. Under this circumstance, a fall is a main factor of accidents at home. From this point of view, we need to detect falls expeditiously and correctly. However, usual methods like using a video camera or a wearable device have some issues in privacy and convenience. In this paper, we propose a system of fall detection using a low resolution infrared array sensor. The proposed system uses this sensor with advantages of privacy protection (low resolution), low cost (cheap sensor), and convenience (small device). We propose four features and based on them, classify activities as either a fall or a non-fall using k-nearest neighbor (k-NN) algorithm. We show a proof-of-concept of our proposed system using a commercial-off-the-shelf (COTS) hardware. Results of experiments show the detection rate of higher than 94 % irrespective of training data contains object's data or not.
UR - https://www.scopus.com/pages/publications/84944324974
UR - https://www.scopus.com/pages/publications/84944324974#tab=citedBy
U2 - 10.1109/PIMRC.2014.7136520
DO - 10.1109/PIMRC.2014.7136520
M3 - Conference contribution
AN - SCOPUS:84944324974
T3 - IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
SP - 2109
EP - 2113
BT - 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication, PIMRC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 25th IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communication, IEEE PIMRC 2014
Y2 - 2 September 2014 through 5 September 2014
ER -