Surveillance in Multi-Camera Systems
(2013) In Master's Theses in Mathematical Sciences FMA820 20131Mathematics (Faculty of Engineering)
- Abstract
- Combining several cameras in a multi-camera system creates a greater overview
of an area than what can be achieved with a single camera. If one of
the cameras have pan, tilt and zoom capability (i.e. a PTZ camera), it can
be used to focus on and track an object moving in the monitored area.
In this project, a method for mapping image coordinates between four fixed
overview cameras and a PTZ camera is developed and tested. It uses SIFT
features to match images against each other in order to find transformations
between the cameras.
An extension for the cameras' built-in tracking for handling object transitions
between the cameras is also developed. Moving objects are tracked in the
overview cameras and the mappings are used to... (More) - Combining several cameras in a multi-camera system creates a greater overview
of an area than what can be achieved with a single camera. If one of
the cameras have pan, tilt and zoom capability (i.e. a PTZ camera), it can
be used to focus on and track an object moving in the monitored area.
In this project, a method for mapping image coordinates between four fixed
overview cameras and a PTZ camera is developed and tested. It uses SIFT
features to match images against each other in order to find transformations
between the cameras.
An extension for the cameras' built-in tracking for handling object transitions
between the cameras is also developed. Moving objects are tracked in the
overview cameras and the mappings are used to direct the PTZ camera to
an object of interest.
The coordinate mapping is found to be accurate in most cases. The method
used for tracking has potential to be useful and some possible improvements
are suggested. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/4172765
- author
- Luong, Annie LU and Schmidt, Christina LU
- supervisor
-
- Erik Ask LU
- organization
- course
- FMA820 20131
- year
- 2013
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3254-2013
- ISSN
- 1404-6342
- other publication id
- 2013:E60
- language
- English
- id
- 4172765
- date added to LUP
- 2014-02-14 16:17:55
- date last changed
- 2014-02-14 16:17:55
@misc{4172765, abstract = {{Combining several cameras in a multi-camera system creates a greater overview of an area than what can be achieved with a single camera. If one of the cameras have pan, tilt and zoom capability (i.e. a PTZ camera), it can be used to focus on and track an object moving in the monitored area. In this project, a method for mapping image coordinates between four fixed overview cameras and a PTZ camera is developed and tested. It uses SIFT features to match images against each other in order to find transformations between the cameras. An extension for the cameras' built-in tracking for handling object transitions between the cameras is also developed. Moving objects are tracked in the overview cameras and the mappings are used to direct the PTZ camera to an object of interest. The coordinate mapping is found to be accurate in most cases. The method used for tracking has potential to be useful and some possible improvements are suggested.}}, author = {{Luong, Annie and Schmidt, Christina}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Surveillance in Multi-Camera Systems}}, year = {{2013}}, }