| | |
Summary: IEEE TRANSACTIONSON PATTERN ANALYSIS AN0 MACHiNE INTELLIGENCE, VOL 21, NO 12, NOVEMBER 1999 1241
N l/perturbedvermn ol R# - R"IZ
2 6 - Z&t*(S,)
Tracking Human Motion
Using a Distributed-CameraSystem
(7) in Structured Environments
From Xo 2 .' ' 2 XZ, and (6) and (7), we have the following result
from which [,I32 can be obtained Q. Cai and J.K. Aggarwal, Fellow, /E
Abstract-This paper presents a comprehensiveframeworklor tracking coarse
multiple camera coordinates. It demonstrates the feasibility of an end-to-end
person tracking system using a unique combination01 motion analysis on 30
z(R#,F) 2 3 x , + 3 x 2 C '3X1 + (G ~ 2Atr(s1))X2' human models from sequencesof synchronized monocular grayscale images in
geometw in different camera Coordinates and other existing techniques in motion
detection,segmentation,and pattem recognition. The system starts with tracking
The authors would like to thank the reviewers for their from a single camera view. When the system predicts that the activecamera will
ACKNOWLEDGMENTS
valuable comments and help. This work was supported by
the Republic of China National Science Council under Grant
NSC-86-2213-E-009-114.
no longer have a good view of the subject of interest,tracking will be switched to
|
