Tracking multiple persons using distributed vision systems.

Accession number;02A0234236
Title;Tracking multiple persons using distributed vision systems.
Author; NAKAZAWA A (Univ. Tokyo) KATO H (Hiroshima City Univ.) HIURA S (Osaka Univ.) INOKUCHI S (Hiroshima City Univ.)
Journal Title;Joho Shori Gakkai Kenkyu Hokoku
Journal Code:Z0031B
ISSN:0919-6072
VOL.2002;NO.2(CVIM-131);PAGE.37-44(2002)
Figure&Table&Reference;FIG.18, REF.6
Pub. Country;Japan
Language;English
Abstract;This paper shows the multiple targets watching method in wide-area spatial environment using the Distributed Vision Systems (DVS). DVS is constructed with some "watching stations" that consist of a camera and an image processor and a computer network connects them. This system's goal is to track multiple persons in a wide-area cannot be watched by one visual sensor. We introduce three algorithms to realize this system, realtime human tracking method, the task decision algorithms of watching stations and the object-matching method between stations. Finally, we describe experimental results that show the validity of our approach. (author abst.)