Advanced

Finding Field of View Overlap by Motion Analysis

Sydvart, Fredrik LU and Altvall, Hampus LU (2017) In Master's Theses in Mathematical Sciences FMA820 20171
Mathematics (Faculty of Engineering)
Abstract
Network cameras has in the recent years become more powerful. Each camera is independent and has its own surveillance task. It is reasonable that network cameras in the future should cooperate together to increase surveillance effectiveness. There is a need to find cameras sharing the same field of view in order for an operator to switch perspective. This thesis investigates how multiple network cameras can cooperate by finding the shared field of view between cameras. With the shared field of view, we implement an additional knowledge above system of network cameras and new use cases arises. Our method consist of applying a grid of cells on each camera's video stream and study movement detection. We gather contradicting proof of... (More)
Network cameras has in the recent years become more powerful. Each camera is independent and has its own surveillance task. It is reasonable that network cameras in the future should cooperate together to increase surveillance effectiveness. There is a need to find cameras sharing the same field of view in order for an operator to switch perspective. This thesis investigates how multiple network cameras can cooperate by finding the shared field of view between cameras. With the shared field of view, we implement an additional knowledge above system of network cameras and new use cases arises. Our method consist of applying a grid of cells on each camera's video stream and study movement detection. We gather contradicting proof of connectedness between each cell in the whole network of cameras. Our method avoids problems with feature detection such as different perspectives or image quality. We found that our method works with promising results and we can find shared field of view between cameras. There is a limitation in memory of storing all cells and we can only find overlap in regions with movement. This field has not been researched so much, making evaluation hard, as many approaches focuses on feature detection. (Less)
Popular Abstract
Network cameras has significantly increased in the recent years. Each camera is independent and its monitoring task can easily be remotely altered. This work focuses on increasing effectiveness of a system of cameras by adding additional knowledge on top of the system and by utilizing multiple cameras when a shared field of view has been found.
Please use this url to cite or link to this publication:
author
Sydvart, Fredrik LU and Altvall, Hampus LU
supervisor
organization
course
FMA820 20171
year
type
H2 - Master's Degree (Two Years)
subject
keywords
surveillance network, network cameras, shared field of view, camera overlap, motion detection
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3332-2017
ISSN
1404-6342
other publication id
2017:E62
language
English
id
8926463
date added to LUP
2017-12-01 15:33:29
date last changed
2018-10-11 16:20:05
@misc{8926463,
  abstract     = {Network cameras has in the recent years become more powerful. Each camera is independent and has its own surveillance task. It is reasonable that network cameras in the future should cooperate together to increase surveillance effectiveness. There is a need to find cameras sharing the same field of view in order for an operator to switch perspective. This thesis investigates how multiple network cameras can cooperate by finding the shared field of view between cameras. With the shared field of view, we implement an additional knowledge above system of network cameras and new use cases arises. Our method consist of applying a grid of cells on each camera's video stream and study movement detection. We gather contradicting proof of connectedness between each cell in the whole network of cameras. Our method avoids problems with feature detection such as different perspectives or image quality. We found that our method works with promising results and we can find shared field of view between cameras. There is a limitation in memory of storing all cells and we can only find overlap in regions with movement. This field has not been researched so much, making evaluation hard, as many approaches focuses on feature detection.},
  author       = {Sydvart, Fredrik and Altvall, Hampus},
  issn         = {1404-6342},
  keyword      = {surveillance network,network cameras,shared field of view,camera overlap,motion detection},
  language     = {eng},
  note         = {Student Paper},
  series       = {Master's Theses in Mathematical Sciences},
  title        = {Finding Field of View Overlap by Motion Analysis},
  year         = {2017},
}