TY - GEN
T1 - Recognition of flow in everyday life using sensor agent robot with laser range finder
AU - Goshima, Misa
AU - Mita, Akira
PY - 2011
Y1 - 2011
N2 - In the present paper, we suggest an algorithm for a sensor agent robot with a laser range finder to recognize the flows of residents in the living spaces in order to achieve flow recognition in the living spaces, recognition of the number of people in spaces, and the classification of the flows. House reform is or will be demanded to prolong the lifetime of the home. Adaption for the individuals is needed for our aging society which is growing at a rapid pace. Home autonomous mobile robots will become popular in the future for aged people to assist them in various situations. Therefore we have to collect various type of information of human and living spaces. However, a penetration in personal privacy must be avoided. It is essential to recognize flows in everyday life in order to assist house reforms and aging societies in terms of adaption for the individuals. With background subtraction, extra noise removal, and the clustering based k-means method, we got an average accuracy of more than 90% from the behavior from 1 to 3 persons, and also confirmed the reliability of our system no matter the position of the sensor. Our system can take advantages from autonomous mobile robots and protect the personal privacy. It hints at a generalization of flow recognition methods in the living spaces.
AB - In the present paper, we suggest an algorithm for a sensor agent robot with a laser range finder to recognize the flows of residents in the living spaces in order to achieve flow recognition in the living spaces, recognition of the number of people in spaces, and the classification of the flows. House reform is or will be demanded to prolong the lifetime of the home. Adaption for the individuals is needed for our aging society which is growing at a rapid pace. Home autonomous mobile robots will become popular in the future for aged people to assist them in various situations. Therefore we have to collect various type of information of human and living spaces. However, a penetration in personal privacy must be avoided. It is essential to recognize flows in everyday life in order to assist house reforms and aging societies in terms of adaption for the individuals. With background subtraction, extra noise removal, and the clustering based k-means method, we got an average accuracy of more than 90% from the behavior from 1 to 3 persons, and also confirmed the reliability of our system no matter the position of the sensor. Our system can take advantages from autonomous mobile robots and protect the personal privacy. It hints at a generalization of flow recognition methods in the living spaces.
KW - Biofication of Living Spaces
KW - Flow Recognition
KW - Laser Range Finder
KW - Sensor Agent Robot
UR - http://www.scopus.com/inward/record.url?scp=79956331754&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79956331754&partnerID=8YFLogxK
U2 - 10.1117/12.879805
DO - 10.1117/12.879805
M3 - Conference contribution
AN - SCOPUS:79956331754
SN - 9780819485434
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
T2 - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
Y2 - 7 March 2011 through 10 March 2011
ER -