Authors:
Koji Kitamura
1
;
Yoshifumi Nishida
2
;
Makoto Kimura
2
and
Hiroshi Mizoguchi
1
Affiliations:
1
Tokyo University of Science, Japan
;
2
Digital Human Research Center, National Insititute of Advanced Industrial Science and Technology (AIST), CREST, JST (Japan Science and Technology Agency), Japan
Keyword(s):
Human Behavior Detection, Ubiquitous Computing, Sensorization, Distributed Sensor.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Enterprise Information Systems
;
Human-Computer Interaction
;
Intelligent User Interfaces
;
Machine Perception: Vision, Speech, Other
Abstract:
This paper describes a method for robustly detecting and efficiently recognizing daily human behavior in real world. The proposed method involves real world sensorization for robustly observing his or her behavior using ultrasonic 3D tags, which is a kind of an ultrasonic location system, real world virtualization for creating a virtual environment through modeling 3D shape of real objects by a stereovision system, and virtual sensorization of the virtualized objects for quickly registering human activities handling objects in real world and efficiently recognizing target human activities. As for real world sensorization, this paper describes algorithms for robustly estimating 3D positions of objects that a human handles. This paper also describes a method for real world virtualization and virtual sensorization using the ultrasonic 3D tag system and a stereovision system.