Advanced search
1 file | 6.81 MB Add to list

Robust multi-camera people tracking using maximum likelihood estimation

Bo Bo Nyan (UGent) , Peter Van Hese (UGent) , Sebastian Grünwedel (UGent) , Junzhi Guan (UGent) , Jorge Niño Castañeda (UGent) , Dirk Van Haerenborgh (UGent) , Dimitri Van Cauwelaert (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
This paper presents a new method to track multiple persons reliably using a network of smart cameras. The task of tracking multiple persons is very challenging due to targets' non-rigid nature, occlusions and environmental changes. Our proposed method estimates the positions of persons in each smart camera using a maximum likelihood estimation and all estimates are merged in a fusion center to generate the final estimates. The performance of our proposed method is evaluated on indoor video sequences in which persons are often occluded by other persons and/or furniture. The results show that our method performs well with the total average tracking error as low as 10.2 cm. We also compared performance of our system to a state-of-the-art tracking system and find that our method outperforms in terms of both total average tracking error and total number of object loss.
Keywords
tracking, smart camera network, maximum likelihood estimation, data fusion, distributed computing

Downloads

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

Citation

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

MLA
Nyan, Bo Bo, et al. “Robust Multi-Camera People Tracking Using Maximum Likelihood Estimation.” Lecture Notes in Computer Science, edited by Jacques Blanc-Talon et al., vol. 8192, Springer, 2013, pp. 584–95.
APA
Nyan, B. B., Van Hese, P., Grünwedel, S., Guan, J., Niño Castañeda, J., Van Haerenborgh, D., … Philips, W. (2013). Robust multi-camera people tracking using maximum likelihood estimation. In J. Blanc-Talon, A. Kasinski, W. Philips, D. Popescu, & P. Scheunders (Eds.), Lecture Notes in Computer Science (Vol. 8192, pp. 584–595). Berlin, Germany: Springer.
Chicago author-date
Nyan, Bo Bo, Peter Van Hese, Sebastian Grünwedel, Junzhi Guan, Jorge Niño Castañeda, Dirk Van Haerenborgh, Dimitri Van Cauwelaert, Peter Veelaert, and Wilfried Philips. 2013. “Robust Multi-Camera People Tracking Using Maximum Likelihood Estimation.” In Lecture Notes in Computer Science, edited by Jacques Blanc-Talon, Andrzej Kasinski, Wilfried Philips, Dan Popescu, and Paul Scheunders, 8192:584–95. Berlin, Germany: Springer.
Chicago author-date (all authors)
Nyan, Bo Bo, Peter Van Hese, Sebastian Grünwedel, Junzhi Guan, Jorge Niño Castañeda, Dirk Van Haerenborgh, Dimitri Van Cauwelaert, Peter Veelaert, and Wilfried Philips. 2013. “Robust Multi-Camera People Tracking Using Maximum Likelihood Estimation.” In Lecture Notes in Computer Science, ed by. Jacques Blanc-Talon, Andrzej Kasinski, Wilfried Philips, Dan Popescu, and Paul Scheunders, 8192:584–595. Berlin, Germany: Springer.
Vancouver
1.
Nyan BB, Van Hese P, Grünwedel S, Guan J, Niño Castañeda J, Van Haerenborgh D, et al. Robust multi-camera people tracking using maximum likelihood estimation. In: Blanc-Talon J, Kasinski A, Philips W, Popescu D, Scheunders P, editors. Lecture Notes in Computer Science. Berlin, Germany: Springer; 2013. p. 584–95.
IEEE
[1]
B. B. Nyan et al., “Robust multi-camera people tracking using maximum likelihood estimation,” in Lecture Notes in Computer Science, Poznań, Poland, 2013, vol. 8192, pp. 584–595.
@inproceedings{4180830,
  abstract     = {This paper presents a new method to track multiple persons reliably using a network of smart cameras. The task of tracking multiple persons is very challenging due to targets' non-rigid nature, occlusions and environmental changes. Our proposed method estimates the positions of persons in each smart camera using a maximum likelihood estimation and all estimates are merged in a fusion center to generate the final estimates. The performance of our proposed method is evaluated on indoor video sequences in which persons are often occluded by other persons and/or furniture. The results show that our method performs well with the total average tracking error as low as 10.2 cm. We also compared performance of our system to a state-of-the-art tracking system and find that our method outperforms in terms of both total average tracking error and total number of object loss.},
  author       = {Nyan, Bo Bo and Van Hese, Peter and Grünwedel, Sebastian and Guan, Junzhi and Niño Castañeda, Jorge and Van Haerenborgh, Dirk and Van Cauwelaert, Dimitri and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {Lecture Notes in Computer Science},
  editor       = {Blanc-Talon, Jacques and Kasinski, Andrzej and Philips, Wilfried and Popescu, Dan and Scheunders, Paul},
  isbn         = {9783319028958},
  issn         = {0302-9743},
  keywords     = {tracking,smart camera network,maximum likelihood estimation,data fusion,distributed computing},
  language     = {eng},
  location     = {Poznań, Poland},
  pages        = {584--595},
  publisher    = {Springer},
  title        = {Robust multi-camera people tracking using maximum likelihood estimation},
  url          = {http://dx.doi.org/10.1007/978-3-319-02895-8_53},
  volume       = {8192},
  year         = {2013},
}

Altmetric
View in Altmetric
Web of Science
Times cited: