Advanced search
1 file | 13.44 MB Add to list

Camera selection for tracking in distributed smart camera networks

Linda Tessens (UGent) , Marleen Morbée (UGent) , Hamid Aghajan (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Tracking persons with multiple cameras with overlapping fields of view instead of with one camera leads to more robust decisions. However, operating multiple cameras instead of one requires more processing power and communication bandwidth, which are limited resources in practical networks. When the fields of view of different cameras overlap, not all cameras are equally needed for localizing a tracking target. When only a selected set of cameras do processing and transmit data to track the target, a substantial saving of resources is achieved. The recent introduction of smart cameras with on-board image processing and communication hardware makes such a distributed implementation of tracking feasible. We present a novel framework for selecting cameras to track people in a distributed smart camera network that is based on generalized information-theory. By quantifying the contribution of one or more cameras to the tracking task, the limited network resources can be allocated appropriately, such that the best possible tracking performance is achieved. With the proposed method, we dynamically assign a subset of all available cameras to each target and track it in difficult circumstances of occlusions and limited fields of view with the same accuracy as when using all cameras.
Keywords
camera selection, multicamera multiobject tracking, Distributed smart camera networks, camera fusion, sensor fusion, viewpoint selection, PEOPLE, SCENE

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 13.44 MB

Citation

Please use this url to cite or link to this publication:

MLA
Tessens, Linda, et al. “Camera Selection for Tracking in Distributed Smart Camera Networks.” ACM TRANSACTIONS ON SENSOR NETWORKS, vol. 10, no. 2, 2014, doi:10.1145/2530281.
APA
Tessens, L., Morbée, M., Aghajan, H., & Philips, W. (2014). Camera selection for tracking in distributed smart camera networks. ACM TRANSACTIONS ON SENSOR NETWORKS, 10(2). https://doi.org/10.1145/2530281
Chicago author-date
Tessens, Linda, Marleen Morbée, Hamid Aghajan, and Wilfried Philips. 2014. “Camera Selection for Tracking in Distributed Smart Camera Networks.” ACM TRANSACTIONS ON SENSOR NETWORKS 10 (2). https://doi.org/10.1145/2530281.
Chicago author-date (all authors)
Tessens, Linda, Marleen Morbée, Hamid Aghajan, and Wilfried Philips. 2014. “Camera Selection for Tracking in Distributed Smart Camera Networks.” ACM TRANSACTIONS ON SENSOR NETWORKS 10 (2). doi:10.1145/2530281.
Vancouver
1.
Tessens L, Morbée M, Aghajan H, Philips W. Camera selection for tracking in distributed smart camera networks. ACM TRANSACTIONS ON SENSOR NETWORKS. 2014;10(2).
IEEE
[1]
L. Tessens, M. Morbée, H. Aghajan, and W. Philips, “Camera selection for tracking in distributed smart camera networks,” ACM TRANSACTIONS ON SENSOR NETWORKS, vol. 10, no. 2, 2014.
@article{8027575,
  abstract     = {{Tracking persons with multiple cameras with overlapping fields of view instead of with one camera leads to more robust decisions. However, operating multiple cameras instead of one requires more processing power and communication bandwidth, which are limited resources in practical networks.

When the fields of view of different cameras overlap, not all cameras are equally needed for localizing a tracking target. When only a selected set of cameras do processing and transmit data to track the target, a substantial saving of resources is achieved. The recent introduction of smart cameras with on-board image processing and communication hardware makes such a distributed implementation of tracking feasible.

We present a novel framework for selecting cameras to track people in a distributed smart camera network that is based on generalized information-theory. By quantifying the contribution of one or more cameras to the tracking task, the limited network resources can be allocated appropriately, such that the best possible tracking performance is achieved.

With the proposed method, we dynamically assign a subset of all available cameras to each target and track it in difficult circumstances of occlusions and limited fields of view with the same accuracy as when using all cameras.}},
  articleno    = {{23}},
  author       = {{Tessens, Linda and Morbée, Marleen and Aghajan, Hamid and Philips, Wilfried}},
  issn         = {{1550-4859}},
  journal      = {{ACM TRANSACTIONS ON SENSOR NETWORKS}},
  keywords     = {{camera selection,multicamera multiobject tracking,Distributed smart camera networks,camera fusion,sensor fusion,viewpoint selection,PEOPLE,SCENE}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{33}},
  title        = {{Camera selection for tracking in distributed smart camera networks}},
  url          = {{http://doi.org/10.1145/2530281}},
  volume       = {{10}},
  year         = {{2014}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: