Real-Time Object Detection with Adaptive Background Model and Margined Sign Correlation

  • Ayaka Yamamoto
  • Yoshio Iwai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5996)


In recent years, the detection accuracy has significantly improved under various conditions using sophisticated methods. However, these methods require a great deal of computational cost, and have difficulty in real-time applications. In this paper, we propose a real-time system for object detection in outdoor environments using a graphics processing unit (GPU). We implement two algorithms on a GPU: adaptive background model, and margined sign correlation. These algorithms can robustly detect moving objects and remove shadow regions. Experimental results demonstrate the real-time performance of the proposed system.


Object detection Real-time system GPU Adaptive background model Margined sign correlation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yoshimura, H., Iwai, Y., Yachida, M.: Object detection with adaptive background model and margined sign cross correlation. In: 18th International Conference on Pattern Recognition, Hong Kong, vol. 3, pp. 19–23 (2006)Google Scholar
  2. 2.
    Huang, K., Wang, L., Tan, T., Maybank, S.: A real-time object detecting and tracking system for outdoor night surveillance. Pattern Recognition 1, 432–444 (2008)CrossRefGoogle Scholar
  3. 3.
    Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practice of background maintenance. In: 7th IEEE International Conference on Computer Vision, Kerkyra, Greece, vol. 1, pp. 255–261 (1999)Google Scholar
  4. 4.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, vol. 2, pp. 246–252 (1999)Google Scholar
  5. 5.
    Monnet, A., Mittal, A., Paragios, N., Ramesh, V.: Background modeling and subtraction of dynamic scene. In: 9th IEEE International Conference on Computer Vision, pp. 1305–1312 (2003)Google Scholar
  6. 6.
    Kaneko, S., Satoh, Y., Igarashi, S.: Robust object detection in image sequence using peripheral increment sign correlation. In: 5th Japan-France Congress on Mechatronics, pp. 287–292 (2001)Google Scholar
  7. 7.
    Price, A., Pyke, J., Achiri, D., Cornall, T.: Real time object detection for an unmanned aerial vehicle using an FPGA based vision system. In: Proceedings 2006 IEEE International Conference on Robotics and Automation, pp. 2854–2859 (2006)Google Scholar
  8. 8.
    Hayashi, H., Nakada, K., Morie, T.: Moving object detection algorithm inspired by the sequence detection in the hippocampus and its digital LSI implementation. International Congress Series, vol. 1301, pp. 35–38 (2007)Google Scholar
  9. 9.
    Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A.E., Purcell, T.J.: A Survey of General-Purpose Computation on Graphics Hardware. Computer Graphics Forum 26, 80–113 (2007)CrossRefGoogle Scholar
  10. 10.
    Zhang, L., Nevatia, R.: Efficient scan-window based object detection using GPGPU. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Anchorage, AK, pp. 1–7 (2008)Google Scholar
  11. 11.
    Fukui, S., Iwahori, Y., Woodham, R.J.: GPU based extraction of moving objects without shadows under intensity changes. In: IEEE Congress on Evolutionary Computation, pp. 4165–4172 (2008)Google Scholar
  12. 12.
    Griesser, A., Roeck, D.S., Neubeck, A., Gool, L.V.: GPU-based foreground-background segmentation using an extended colinearity criterion. In: Proceedings of Vision, Modeling and Visualization 2005, pp. 319–326 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ayaka Yamamoto
    • 1
  • Yoshio Iwai
    • 1
  1. 1.Graduate School of Engneering ScienceOsaka UniversityOsakaJapan

Personalised recommendations