Vehicle Detection Algorithm for FPGA Based Implementation

  • Wieslaw Pamula
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 57)


The paper presents a discussion of necessary properties of an algorithm processing a real world video stream for detecting vehicles in defined detection fields and proposes a robust solution which is suitable for FPGA based implementation. The solution is build on spatiotemporal filtering supported by a modified recursive approximation of the temporal median of the detection fields ocupancy factors. The resultant algorithm may process image pixels serially which is an especially desirable property when devising logic based processing hardware.


Video Stream Illumination Change Vehicle Detection Occupancy Factor Recursive Approximation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wu, Y., Shen, J., Dai, M.: Traffic object detections and it’s action analysis. Pattern Recognition Letters 26, 1963–1984 (2005)Google Scholar
  2. 2.
    Michalopoulos, P.G.: Vehicle detection video through image processing: the autoscope system. IEEE Trans. Vehicular Technol. 40(1), 21–29 (1991)CrossRefGoogle Scholar
  3. 3.
    Coifman, B., Beymer, D., McLauchlan, P., Malik, J.: A real-time computer vision system for vehicle tracking and traffic surveillance. Transport Research Part C: Emerging Technologies 6(4), 271–278 (1998)CrossRefGoogle Scholar
  4. 4.
    Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans. Pattern Analysis Machine Intelligence 25, 1337–1342 (2003)CrossRefGoogle Scholar
  5. 5.
    Manzanera, A., Richefeu, J.C.: A new motion detection algorithm based on Σ − Δ background estimation. Pattern Recognition Letters 28, 320–328 (2007)CrossRefGoogle Scholar
  6. 6.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 246–252 (1999)Google Scholar
  7. 7.
    KaewTraKulPong, P., Bowden, R.: An Improved Adaptive Background Mixture Model for Realtime Tracking with Shadow Detection. In: Proc. 2nd European Workshop on Advanced Video Based Surveillance Systems, AVBS 2001. Video based surveillace systems. Computer Vision and Distributed Processing. Kluwer Academic Publishers, Dordrecht (2001)Google Scholar
  8. 8.
    Bhandakar, S.M., Luo, X.: Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 278–284 (2005)Google Scholar
  9. 9.
    Yadav, R.B., Nishchal, N.K., Gupta, A.K., Rastogi, V.K.: Retrieval and classification of shape-based objects using Fourier, generic Fourier, and wavelet-Fourier descriptors technique: A comparative study. Optics and Lasers in Engineering 45, 695–708 (2007)CrossRefGoogle Scholar
  10. 10.
    Suna, Z., Bebisa, G., Miller, R.: Object detection using feature subset selection. Pattern Recognition 37, 2165–2176 (2004)CrossRefGoogle Scholar
  11. 11.
    Project Report: Modules of Video Traffic Incidents Detectors ZIR-WD for Road Traffic Control and Surveillance. WKP-1/1.4.1/1/2005/14/14/231/2005, vol. 1-6, Katowice, Poland (2007)Google Scholar
  12. 12.
    Damasevicius, R., Stuikys, V.: Application of the object-oriented principles for hardware and embedded system design. Integration the VLSI Journal 38, 309–339 (2004)Google Scholar
  13. 13.
    Murata, T.: Petri Nets: Properties, Analysis and Applications. Proceedings of the IEEE 77, 541–580 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Wieslaw Pamula
    • 1
  1. 1.Faculty of TransportSilesian University of TechnologyKatowicePoland

Personalised recommendations