These days, video surveillance is an important security asset to control theft, trespassing or traffic monitoring for any physical systems, whether personal or commercial. Implementing a surveillance system can allow people to get an idea of what is going on without the physical need to be there. In the classical video surveillance installations, there is a need for a human operator to consistently watch the video feed to see if there is any interesting activity. An intelligent, computer vision-based motion detector eliminates the need for constant surveillance by an operator by notifying an interested party that there is relevant motion in the area being monitored.
Pan tilt zoom (PTZ) cameras can be used to track an object of interest moving throughout a scene. However, in classic systems, this again would require the operator to manually move the PTZ camera to get the subject in scope. The goal of this work is to eliminate the operator from controlling the system. With the proposed automated tracking approach, an object found in a scene can be tracked automatically and followed until the target is out of camera scope. / Graduate
| Identifer | oai:union.ndltd.org:uvic.ca/oai:dspace.library.uvic.ca:1828/4145 |
| Date | 21 August 2012 |
| Creators | Quevillon, Joey |
| Contributors | Branzan-Albu, Alexandra |
| Source Sets | University of Victoria |
| Language | English, English |
| Detected Language | English |
| Type | Thesis |
| Rights | Available to the World Wide Web |
Page generated in 0.0023 seconds