Advanced search
1 file | 684.55 KB

Template matching based people tracking using a smart camera network

Junzhi Guan (UGent) , Peter Van Hese (UGent) , Jorge Niño Castañeda (UGent) , Bo Bo Nyan (UGent) , Sebastian Grünwedel (UGent) , Dirk Van Haerenborgh (UGent) , Dimitri Van Cauwelaert (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
(2014) Proceedings of SPIE. 9026. p.90260Y-1-90260Y-9
Author
Organization
Abstract
In this paper, we proposes a people tracking system composed of multiple calibrated smart cameras and one fusion server which fuses the information from all cameras. Each smart camera estimates the ground plane positions of people based on the current frame and feedback from the server from the previous time. Correlation coefficient based template matching, which is invariant to illumination changes, is proposed to estimate the position of people in each smart camera. Only the estimated position and the corresponding correlation coefficient are sent to the server. This minimal amount of information exchange makes the system highly scalable with the number of cameras. The paper focuses on creating and updating a good template for the tracked person using feedback from the server. Additionally, a static background image of the empty room is used to improve the results of template matching. We evaluated the performance of the tracker in scenarios where persons are often occluded by other persons or furniture, and illumination changes occur frequently e.g., due to switching the light on or off. For two sequences (one minute for each, one with table in the room, one without table) with frequent illumination changes, the proposed tracker never lose track of the persons. We compare the performance of our tracking system to a state-of-the-art tracking system. Our approach outperforms it in terms of tracking accuracy and people loss.
Keywords
smart camera network, occlusion, template matching, illumination, people tracking

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 684.55 KB

Citation

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

Chicago
Guan, Junzhi, Peter Van Hese, Jorge Niño Castañeda, Bo Bo Nyan, Sebastian Grünwedel, Dirk Van Haerenborgh, Dimitri Van Cauwelaert, Peter Veelaert, and Wilfried Philips. 2014. “Template Matching Based People Tracking Using a Smart Camera Network.” In Proceedings of SPIE, ed. Robert P Loce and Eli Saber, 9026:90260Y–1–90260Y–9. San Francisco, California, USA: SPIE-INT SOC OPTICAL ENGINEERING.
APA
Guan, J., Van Hese, P., Niño Castañeda, J., Nyan, B. B., Grünwedel, S., Van Haerenborgh, D., Van Cauwelaert, D., et al. (2014). Template matching based people tracking using a smart camera network. In Robert P Loce & E. Saber (Eds.), Proceedings of SPIE (Vol. 9026, pp. 90260Y–1–90260Y–9). Presented at the Conference on Video Surveillance and Transportation Imaging Applications, San Francisco, California, USA: SPIE-INT SOC OPTICAL ENGINEERING.
Vancouver
1.
Guan J, Van Hese P, Niño Castañeda J, Nyan BB, Grünwedel S, Van Haerenborgh D, et al. Template matching based people tracking using a smart camera network. In: Loce RP, Saber E, editors. Proceedings of SPIE. San Francisco, California, USA: SPIE-INT SOC OPTICAL ENGINEERING; 2014. p. 90260Y–1–90260Y–9.
MLA
Guan, Junzhi, Peter Van Hese, Jorge Niño Castañeda, et al. “Template Matching Based People Tracking Using a Smart Camera Network.” Proceedings of SPIE. Ed. Robert P Loce & Eli Saber. Vol. 9026. San Francisco, California, USA: SPIE-INT SOC OPTICAL ENGINEERING, 2014. 90260Y–1–90260Y–9. Print.
@inproceedings{4425949,
  abstract     = {In this paper, we proposes a people tracking system composed of multiple calibrated smart cameras and one fusion server which fuses the information from all cameras. Each smart camera estimates the ground plane positions of people based on the current frame and feedback from the server from the previous time. Correlation coefficient based template matching, which is invariant to illumination changes, is proposed to estimate the position of people in each smart camera. Only the estimated position and the corresponding correlation coefficient are sent to the server. This minimal amount of information exchange makes the system highly scalable with the number of cameras. The paper focuses on creating and updating a good template for the tracked person using feedback from the server. Additionally, a static background image of the empty room is used to improve the results of template matching. We evaluated the performance of the tracker in scenarios where persons are often occluded by other persons or furniture, and illumination changes occur frequently e.g., due to switching the light on or off. For two sequences (one minute for each, one with table in the room, one without table) with frequent illumination changes, the proposed tracker never lose track of the persons. We compare the performance of our tracking system to a state-of-the-art tracking system. Our approach outperforms it in terms of tracking accuracy and people loss.},
  articleno    = {90260Y},
  author       = {Guan, Junzhi and Van Hese, Peter and Ni{\~n}o Casta{\~n}eda, Jorge and Nyan, Bo Bo and Gr{\"u}nwedel, Sebastian and Van Haerenborgh, Dirk and Van Cauwelaert, Dimitri and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {Proceedings of SPIE},
  editor       = {Loce, Robert P and Saber, Eli},
  isbn         = {9780819499431},
  issn         = {0277-786X},
  keyword      = {smart camera network,occlusion,template matching,illumination,people tracking},
  language     = {eng},
  location     = {San Francisco, California, USA},
  pages        = {90260Y:90260Y-1--90260Y:90260Y-9},
  publisher    = {SPIE-INT SOC OPTICAL ENGINEERING},
  title        = {Template matching based people tracking using a smart camera network},
  url          = {http://dx.doi.org/10.1117/12.2036745},
  volume       = {9026},
  year         = {2014},
}

Altmetric
View in Altmetric
Web of Science
Times cited: