DMCA
Multi-camera calibration, object tracking and query generation
| Venue: | in Proc. Int. Conf. Multimedia and Expo, 2003 |
| Citations: | 29 - 0 self |
BibTeX
@INPROCEEDINGS{Divakaran_multi-cameracalibration,,
author = {F. Divakaran and Fatih Porikli and Ajay Divakaran},
title = {Multi-camera calibration, object tracking and query generation},
booktitle = {in Proc. Int. Conf. Multimedia and Expo, 2003},
year = {},
pages = {653--656}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
An automatic object tracking and video summarization method for multi-camera systems with a large number of non-overlapping field-of-view cameras is explained. In this framework, video sequences are stored for each object as opposed to storing a sequence for each camera. Objectbased representation enables annotation of video segments, and extraction of content semantics for further analysis. We also present a novel solution to the inter-camera color calibration problem. The transitive model function enables effective compensation for lighting changes and radiometric distortions for large-scale systems. After initial calibration, objects are tracked at each camera by background subtraction and mean-shift analysis. The correspondence of objects between different cameras is established by using a Bayesian Belief Network. This framework empowers the user to get a concise response to queries such as which locations did an object visit on Monday and what did it do there?
Keyphrases
multi-camera calibration object tracking query generation video sequence non-overlapping field-of-view camera multi-camera system initial calibration automatic object tracking large number radiometric distortion different camera novel solution bayesian belief network video segment video summarization method large-scale system content semantics concise response object visit inter-camera color calibration problem background subtraction mean-shift analysis
