Advanced search
1 file | 1.67 MB

Extrinsic calibration of camera networks based on pedestrians

(2016) SENSORS. 16(5).
Author
Organization
Abstract
In this paper, we propose a novel extrinsic calibration method for camera networks by analyzing tracks of pedestrians. First of all, we extract the center lines of walking persons by detecting their heads and feet in the camera images. We propose an easy and accurate method to estimate the 3D positions of the head and feet w.r.t. a local camera coordinate system from these center lines. We also propose a RANSAC-based orthogonal Procrustes approach to compute relative extrinsic parameters connecting the coordinate systems of cameras in a pairwise fashion. Finally, we refine the extrinsic calibration matrices using a method that minimizes the reprojection error. While existing state-of-the-art calibration methods explore epipolar geometry and use image positions directly, the proposed method first computes 3D positions per camera and then fuses the data. This results in simpler computations and a more flexible and accurate calibration method. Another advantage of our method is that it can also handle the case of persons walking along straight lines, which cannot be handled by most of the existing state-of-the-art calibration methods since all head and feet positions are co-planar. This situation often happens in real life.
Keywords
camera network, orthogonal Procrustes, pedestrians, extrinsic calibration, CLOSED-FORM SOLUTION, AUTOCALIBRATION, SURVEILLANCE, QUATERNIONS, SURFACES, VISION, MODEL

Downloads

  • sensors-16-00654.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.67 MB

Citation

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

Chicago
Guan, Junzhi, Francis Deboeverie, Maarten Slembrouck, Dirk Van Haerenborgh, Dimitri Van Cauwelaert, Peter Veelaert, and Wilfried Philips. 2016. “Extrinsic Calibration of Camera Networks Based on Pedestrians.” Ed. Fabrizio Lamberti. Sensors 16 (5).
APA
Guan, J., Deboeverie, F., Slembrouck, M., Van Haerenborgh, D., Van Cauwelaert, D., Veelaert, P., & Philips, W. (2016). Extrinsic calibration of camera networks based on pedestrians. (Fabrizio Lamberti, Ed.)SENSORS, 16(5).
Vancouver
1.
Guan J, Deboeverie F, Slembrouck M, Van Haerenborgh D, Van Cauwelaert D, Veelaert P, et al. Extrinsic calibration of camera networks based on pedestrians. Lamberti F, editor. SENSORS. Basel, Switzerland: MDPI AG; 2016;16(5).
MLA
Guan, Junzhi, Francis Deboeverie, Maarten Slembrouck, et al. “Extrinsic Calibration of Camera Networks Based on Pedestrians.” Ed. Fabrizio Lamberti. SENSORS 16.5 (2016): n. pag. Print.
@article{7205439,
  abstract     = {In this paper, we propose a novel extrinsic calibration method for camera networks by analyzing tracks of pedestrians. First of all, we extract the center lines of walking persons by detecting their heads and feet in the camera images. We propose an easy and accurate method to estimate the 3D positions of the head and feet w.r.t. a local camera coordinate system from these center lines. We also propose a RANSAC-based orthogonal Procrustes approach to compute relative extrinsic parameters connecting the coordinate systems of cameras in a pairwise fashion. Finally, we refine the extrinsic calibration matrices using a method that minimizes the reprojection error. While existing state-of-the-art calibration methods explore epipolar geometry and use image positions directly, the proposed method first computes 3D positions per camera and then fuses the data. This results in simpler computations and a more flexible and accurate calibration method. Another advantage of our method is that it can also handle the case of persons walking along straight lines, which cannot be handled by most of the existing state-of-the-art calibration methods since all head and feet positions are co-planar. This situation often happens in real life.},
  articleno    = {654},
  author       = {Guan, Junzhi and Deboeverie, Francis and Slembrouck, Maarten and Van Haerenborgh, Dirk and Van Cauwelaert, Dimitri and Veelaert, Peter and Philips, Wilfried},
  editor       = {Lamberti, Fabrizio},
  issn         = {1424-8220},
  journal      = {SENSORS},
  keyword      = {camera network,orthogonal Procrustes,pedestrians,extrinsic calibration,CLOSED-FORM SOLUTION,AUTOCALIBRATION,SURVEILLANCE,QUATERNIONS,SURFACES,VISION,MODEL},
  language     = {eng},
  number       = {5},
  publisher    = {MDPI AG},
  title        = {Extrinsic calibration of camera networks based on pedestrians},
  url          = {http://dx.doi.org/10.3390/s16050654},
  volume       = {16},
  year         = {2016},
}

Altmetric
View in Altmetric
Web of Science
Times cited: