ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper CNN based Infant Behavior Estimation
Cited - time in scopus Download 14 time Share share facebook twitter linkedin kakaostory
Authors
Yejin Lee, Kye Kyung Kim
Issue Date
2019-06
Citation
International Conference on Ubiquitous Robots (UR) 2019, pp.1-2
Publisher
IEEE
Language
English
Type
Conference Paper
Project Code
19PS1300, Development of Intelligent Platform for Living Safety Service in the Complex Living Space, Kye Kyung Kim
Abstract
Infant safety accidents are increasing in the home environment. In order to prevent this, there are growing cases in which devices and systems are installed in the home environment to monitor infant. These recent cameras are able to monitor infant, but without intelligent analysis. Proper monitoring of infant and young children requires intelligent analysis. Because there is a problem that should keep watching infant risk situation, we need a system that analyzes the dangerous situation and notifies the protector. Furthermore, analyzing the behavior of infant requires intelligent analysis because early diagnosis of diseases such as cerebral palsy is possible. It is important to precisely estimate the behavior of the infant in order to develop such a technique. In this paper, we will diagnose the infant two risk situations as suffocation and cerebral palsy. Normally, the head of the infant turns on the face detection only. In case of face detection misrecognized, we will analyze infant risk situation more precisely by analyzing infant face detection and body detection together.
KSP Keywords
And systems, Behavior Estimation, Cerebral Palsy, Early diagnosis, Face detection, Home environment, Infant safety, Intelligent analysis, Safety accidents, body detection, diagnosis of diseases