| Paper: | TA-P1.1 |
| Session: | Video Surveillance I / Document Image Processing & Analysis |
| Time: | Tuesday, September 18, 09:50 - 12:30 |
| Presentation: |
Poster
|
| Title: |
A MULTI-CAMERA SURVEILLANCE SYSTEM THAT ESTIMATES QUALITY-OF-VIEW MEASUREMENT |
| Authors: |
Changsong Shen; University of British Columbia | | |
| | Chris Zhang; University of British Columbia | | |
| | Sidney Fels; University of British Columbia | | |
| Abstract: |
In this paper, we propose a multi-camera video surveillance with automatic camera selection. A new confidence measure, Quality-Of-View (QOV), is defined to automatically evaluate the camera’s view performance for each time instant. View angle and distance between subjects and cameras are utilized in this concept. By comparing their QOVs, the system can select the most appropriate cameras to perform specific tasks. We also present an approach to determine the minimum number of cameras and their layout in a convex polygonal room based on the QOV constraints. Finally, we implement an experimental surveillance system, to confirm the stability of our algorithm and validate the critical underlying concepts of QOV. |
