Advanced search
1 file | 307.68 KB

Vehicle classification for road tunnel surveillance

Author
Organization
Abstract
Vehicle classification for tunnel surveillance aims to not only retrieve vehicle class statistics, but also prevent accidents by recognizing vehicles carrying dangerous goods. In this paper, we describe a method to classify vehicle images that experience different geometrical variations and challenging photometrical conditions such as those found in road tunnels. Unlike previous approaches, we propose a classification method that does not rely on the length and height estimation of the vehicles. Alternatively, we propose a novel descriptor based on trace transform signatures to extract salient and non-correlated information of the vehicle images. Also, we propose a metric that measures the complexity of the vehicles’ shape based on corner point detection. As a result, these features describe the vehicle’s appearance and shape complexity independently of the scale, pose, and illumination conditions. Experiments with vehicles captured from three different cameras confirm the saliency and robustness of the features proposed, achieving an overall accuracy of 97.5% for the classification of four different vehicle classes. For vehicles transporting dangerous goods, our classification scheme achieves an average recall of 97.6% at a precision of 98.6% for the combination of lorries and tankers, which is a very good result considering the scene conditions.
Keywords
Shape complexity., Vehicle classification, Trace transform, Tunnel surveillance

Downloads

  • article.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 307.68 KB

Citation

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

Chicago
Frias Velazquez, Andres, Peter Van Hese, Aleksandra Pizurica, and Wilfried Philips. 2013. “Vehicle Classification for Road Tunnel Surveillance.” In Video Surveillance and Transportation Imaging Applications, ed. Robert Paul Loce, Eli Saber, and Sreenath Rao Vantaram. Vol. 8663. Spie.
APA
Frias Velazquez, A., Van Hese, P., Pizurica, A., & Philips, W. (2013). Vehicle classification for road tunnel surveillance. In Robert Paul Loce, E. Saber, & S. Rao Vantaram (Eds.), Video Surveillance and Transportation Imaging Applications (Vol. 8663). Presented at the Conference on Video Surveillance and Transportation Imaging Applications, Spie.
Vancouver
1.
Frias Velazquez A, Van Hese P, Pizurica A, Philips W. Vehicle classification for road tunnel surveillance. In: Loce RP, Saber E, Rao Vantaram S, editors. Video Surveillance and Transportation Imaging Applications. Spie; 2013.
MLA
Frias Velazquez, Andres, Peter Van Hese, Aleksandra Pizurica, et al. “Vehicle Classification for Road Tunnel Surveillance.” Video Surveillance and Transportation Imaging Applications. Ed. Robert Paul Loce, Eli Saber, & Sreenath Rao Vantaram. Vol. 8663. Spie, 2013. Print.
@inproceedings{3127653,
  abstract     = {Vehicle classification for tunnel surveillance aims to not only retrieve vehicle class statistics, but also prevent accidents by recognizing vehicles carrying dangerous goods. In this paper, we describe a method to classify vehicle images that experience different geometrical variations and challenging photometrical conditions such as those found in road tunnels. Unlike previous approaches, we propose a classification method that does not rely on the length and height estimation of the vehicles. Alternatively, we propose a novel descriptor based on trace transform signatures to extract salient and non-correlated information of the vehicle images. Also, we propose a metric that measures the complexity of the vehicles{\textquoteright} shape based on corner point detection. As a result, these features describe the vehicle{\textquoteright}s appearance and shape complexity independently of the scale, pose, and illumination conditions. Experiments with vehicles captured from three different cameras confirm the saliency and robustness of the features proposed, achieving an overall accuracy of 97.5\% for the classification of four different vehicle classes. For vehicles transporting dangerous goods, our classification scheme achieves an average recall of 97.6\% at a precision of 98.6\% for the combination of lorries and tankers, which is a very good result considering the scene conditions.},
  articleno    = {86630M},
  author       = {Frias Velazquez, Andres and Van Hese, Peter and Pizurica, Aleksandra and Philips, Wilfried},
  booktitle    = {Video Surveillance and Transportation Imaging Applications},
  editor       = {Loce, Robert Paul  and Saber, Eli  and Rao Vantaram, Sreenath },
  isbn         = {9780819494368},
  issn         = {0277-786X},
  keyword      = {Shape complexity.,Vehicle classification,Trace transform,Tunnel surveillance},
  language     = {eng},
  location     = {Burlingame, CA, USA},
  pages        = {6},
  publisher    = {Spie},
  title        = {Vehicle classification for road tunnel surveillance},
  url          = {http://dx.doi.org/10.1117/12.2008190},
  volume       = {8663},
  year         = {2013},
}

Altmetric
View in Altmetric
Web of Science
Times cited: