Adaptive human motion tracking using non-synchronous multiple viewpoint observations

Author

Utsumi, Akira ; Yang, Howard ; Ohya, Jun

Author_Institution

ATR Media Integration & Commun. Res. Labs., Kyoto, Japan

Volume

4

fYear

2000

fDate

2000

Firstpage

607

Abstract

We propose an adaptive human tracking system with non-synchronous multiple observations. Our system consists of three types of processes: discovering node for detecting newly appeared person; tracking node for tracking each target person; and observation node for processing one viewpoint (camera) images. We have multiple observation nodes and each node works independently. The tracking node integrates the observed information based on reliability evaluation. Both the observation conditions and human motion states are considered in the evaluation. Matching between tracking models and observed image features are performed in each of the observation node based on the position, size and color similarities of each 2D image. Due to the non-synchronous property, this system is highly scalable for increasing the detection area and number of observing nodes. Experimental results for some indoor scenes are also described

Keywords

computer vision; feature extraction; image colour analysis; motion estimation; object recognition; target tracking; adaptive tracking; computer vision; feature extraction; human motion tracking; image color analysis; image matching; motion state detection; multiple viewpoint observations; object recognition; target tracking; Adaptive systems; Application software; Cameras; Computer vision; Humans; Layout; Legged locomotion; Surveillance; Target tracking; User interfaces;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.902992

Filename

902992