Using adaptive tracking to classify and monitor activities in a site

被引：231

作者：

Grimson, WEL ^{[1
]}

Stauffer, C ^{[1
]}

Romano, R ^{[1
]}

Lee, L ^{[1
]}

机构：

[1] MIT, Artificial Intelligence Lab, Cambridge, MA 02139 USA

来源：

1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/CVPR.1998.698583

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe a vision system that monitors activity in a Site over extended periods of time. The system uses a distributed set of sensors to cover the site, and an adaptive trader detects multiple moving objects in the sensors. Our hypothesis is that motion tracking is sufficient to support a range of computations about site activities. I We demonstrate using the tracked motion data: to calibrate the distributed sensors, to con Struct rough Site models, to classify detected objects, to learn common patterns of activity for different object classes, and to detect unusual activities.

引用

页码：22 / 29

页数：8