Realtime personal positioning system for a wearable computer

Author

Aoki, Hisashi ; Schiele, Bernt ; Pentlan, Alex

Author_Institution

Media Lab., MIT, Cambridge, MA, USA

fYear

1999

fDate

18-19 Oct. 1999

Firstpage

37

Lastpage

43

Abstract

Context awareness is an important functionality for wearable computers. In particular, the computer should know where the person is in the environment. This paper proposes an image sequence matching technique for the recognition of locations and previously visited places. As in single word recognition in speech recognition, a dynamic programming algorithm is proposed for the calculation of the similarity of different locations. The system runs on a standalone wearable computer, such as a Libretto PC. Using a training sequence, a dictionary of locations is created automatically. These locations are then recognized by the system in real time using a hat-mounted camera.

Keywords

computerised instrumentation; dictionaries; dynamic programming; image matching; image sequences; microcomputer applications; personal computing; portable computers; position measurement; real-time systems; Libretto PC; dynamic programming algorithm; hat-mounted camera; image sequence matching technique; location dictionary; location recognition; location similarity; previously visited places; real-time personal positioning system; training sequence; wearable computer; Automatic speech recognition; Context awareness; Dictionaries; Dynamic programming; Heuristic algorithms; Image recognition; Image sequences; Real time systems; Speech recognition; Wearable computers;

fLanguage

English

Publisher

ieee

Conference_Titel

Wearable Computers, 1999. Digest of Papers. The Third International Symposium on

Conference_Location

San Francisco, CA, USA

Print_ISBN

0-7695-0428-0

Type

conf

DOI

10.1109/ISWC.1999.806642

Filename

806642