Advanced search
1 file | 1.98 MB

Image projection clues for improved real-time vehicle tracking in tunnels

Author
Organization
Abstract
Vehicle tracking is of great importance for tunnel safety. To detect incidents or disturbances in traffic flow it is necessary to reliably track vehicles in real-time. The tracking is a challenging task due to poor lighting conditions in tunnels and frequent light reflections from tunnel walls, the road and the vehicles themselves. In this paper we propose a multi-clue tracking approach combining foreground blobs, optical flow of Shi-Tomasi features and image projection profiles in a Kalman filter with a constant velocity model. The main novelty of our approach lies in using vertical and horizontal image projection profiles (so-called vehicle signatures) as additional measurements to overcome the problems of inconsistent foreground and optical flow clues in cases of severe lighting changes. These signatures consist of Radon-transform like projections along each image column and row. We compare the signatures from two successive video frames to find their alignment and to correct predicted vehicle position and size. We tested our approach on several tunnel sequences. The results show an improvement in the accuracy of the tracker and less target losses when image projection clues are used. Furthermore, calculation and comparison of image projections is computationally efficient so the tracker keeps real-time performance (25 fps, on a single 1.86 GHz processor).
Keywords
feature extraction, FEATURES, traffic monitoring, Real-time tracking of vehicles, tunnel surveillance

Downloads

    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.98 MB

Citation

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

Chicago
Jelača, Vedran, Jorge Niño Castañeda, Aleksandra Pizurica, and Wilfried Philips. 2012. “Image Projection Clues for Improved Real-time Vehicle Tracking in Tunnels.” In Proceedings of Spie, the International Society for Optical Engineering, ed. J Roning and DP Casasent. Vol. 8301. Bellingham, WA, USA: SPIE.
APA
Jelača, V., Niño Castañeda, J., Pizurica, A., & Philips, W. (2012). Image projection clues for improved real-time vehicle tracking in tunnels. In J. Roning & D. Casasent (Eds.), PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING (Vol. 8301). Presented at the Conference on Intelligent Robots and Computer Vision XXIX - Algorithms and Techniques, Bellingham, WA, USA: SPIE.
Vancouver
1.
Jelača V, Niño Castañeda J, Pizurica A, Philips W. Image projection clues for improved real-time vehicle tracking in tunnels. In: Roning J, Casasent D, editors. PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING. Bellingham, WA, USA: SPIE; 2012.
MLA
Jelača, Vedran, Jorge Niño Castañeda, Aleksandra Pizurica, et al. “Image Projection Clues for Improved Real-time Vehicle Tracking in Tunnels.” Proceedings of Spie, the International Society for Optical Engineering. Ed. J Roning & DP Casasent. Vol. 8301. Bellingham, WA, USA: SPIE, 2012. Print.
@inproceedings{2027415,
  abstract     = {Vehicle tracking is of great importance for tunnel safety. To detect incidents or disturbances in traffic flow it is necessary to reliably track vehicles in real-time. The tracking is a challenging task due to poor lighting conditions in tunnels and frequent light reflections from tunnel walls, the road and the vehicles themselves. In this paper we propose a multi-clue tracking approach combining foreground blobs, optical flow of Shi-Tomasi features and image projection profiles in a Kalman filter with a constant velocity model. The main novelty of our approach lies in using vertical and horizontal image projection profiles (so-called vehicle signatures) as additional measurements to overcome the problems of inconsistent foreground and optical flow clues in cases of severe lighting changes. These signatures consist of Radon-transform like projections along each image column and row. We compare the signatures from two successive video frames to find their alignment and to correct predicted vehicle position and size. We tested our approach on several tunnel sequences. The results show an improvement in the accuracy of the tracker and less target losses when image projection clues are used. Furthermore, calculation and comparison of image projections is computationally efficient so the tracker keeps real-time performance (25 fps, on a single 1.86 GHz processor).},
  articleno    = {83010C},
  author       = {Jela\v{c}a, Vedran and Ni{\~n}o Casta{\~n}eda, Jorge and Pizurica, Aleksandra and Philips, Wilfried},
  booktitle    = {PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING},
  editor       = {Roning, J and Casasent, DP},
  isbn         = {9780819489487},
  issn         = {0277-786X},
  keyword      = {feature extraction,FEATURES,traffic monitoring,Real-time tracking of vehicles,tunnel surveillance},
  language     = {eng},
  location     = {Burlingame, CA, USA},
  pages        = {7},
  publisher    = {SPIE},
  title        = {Image projection clues for improved real-time vehicle tracking in tunnels},
  url          = {http://dx.doi.org/10.1117/12.908873},
  volume       = {8301},
  year         = {2012},
}

Altmetric
View in Altmetric
Web of Science
Times cited: