Real-Time Background Compensation for PTZ Cameras Using GPU Accelerated and Range-Limited Genetic Algorithm Search

  • Thuy Tuong Nguyen
  • Jae Wook Jeon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7087)


We propose a range-limited Genetic Algorithm (GA) search with an accelerated Graphics Processing Unit (GPU) based implementation for background compensation where pan-tilt-zoom (PTZ) cameras are used. Our method contains GA with search ranges restricted using histogram matching and GPU implementation of the range-limited GA. First, based on histogram matching, estimation of approximate scale (camera zoom) and translation (camera pan and tilt) parameters is used to restrict the ranges for the later GA search. Next, the GA is applied to find an optimal solution. Experimental comparisons of the proposed method to existing methods show that our work has advantages: robust to critical situations due to using GA, and fast processing.


Background compensation histogram matching GA GPU 


  1. 1.
    Suhr, J.K., Jung, H.G., Li, G., Noh, S.I., Kim, J.H.: Background Compensation for Pan-Tilt-Zoom Cameras using 1-D Feature Matching and Outlier Rejection. IEEE Trans. Circuits Syst. Video Technol. 21(3), 371–377 (2011)CrossRefGoogle Scholar
  2. 2.
    Murray, D., Basu, A.: Motion Tracking with an Active Camera. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 449–459 (1994)CrossRefGoogle Scholar
  3. 3.
    Araki, S., Matsuoka, T., Yokoya, N., Takemura, H.: Real-time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence. IEICE Trans. Inform. Syst. E83–D(7), 1583–1591 (2000)Google Scholar
  4. 4.
    Odobez, J., Bouthemy, P., Temis, P.: Robust Multi-resolution Estimation of Parametric Motion Models in Complex Image Sequences. J. Vis. Commun. Image Represent. 6, 348–365 (1995)CrossRefGoogle Scholar
  5. 5.
    Pham, X.D., Cho, J.U., Jeon, J.W.: Background Compensation using Hough Transformation. In: IEEE Int. Conf. Robot. Autom., pp. 2392–2397 (2008)Google Scholar
  6. 6.
    Moscheni, F., Vesin, J.: A Genetic Algorithm for Motion Estimation. In: 15eme Colloque sur le Traitement des Signaux et Images, France, pp. 825–828 (1995)Google Scholar
  7. 7.
    Gong, M., Yang, Y.H.: Quadtree-Based Genetic Algorithm and Its Applications to Computer Vision. Pattern Recognit. 37(8), 1723–1733 (2004)CrossRefzbMATHGoogle Scholar
  8. 8.
    Rodehorst, V., Hellwich, O.: Genetic Algorithm Sample Consensus (GASAC) - A Parallel Strategy for Robust Parameter Estimation. In: IEEE Int. Conf. Comput. Vis. Pattern Recognit. Workshop, pp. 103–110 (2006)Google Scholar
  9. 9.
    Mutoh, A., Nakamura, T., Kato, S., Itoh, H.: Reducing Execution Time on Genetic Algorithm in Real-World Applications using Fitness Prediction: Parameter Optimization of SRM Control. In: IEEE Congress Evol. Comput., pp. 552–559 (2003)Google Scholar
  10. 10.
    Jin, Y., Sendhoff, B.: Reducing Fitness Evaluations using Clustering Techniques and Neural Network Ensembles. In: Genetic Evol. Comput. Conf., pp. 688–699 (2004)Google Scholar
  11. 11.
    Shams, R., Kennedy, R.A.: Efficient Histogram Algorithms for NVIDIA CUDA Compatible Devices. In: Int. Conf. Signal Process. and Commun. Syst., pp. 418–422 (2007)Google Scholar
  12. 12.
    Tzeng, S., Wei, L.Y.: Parallel White Noise Generation on a GPU via Cryptographic Hash. In: Symp. on Interactive 3D Graphics and Games, pp. 79–87 (2008)Google Scholar
  13. 13.
    Harris, M., Sengupta, S., Owens, J.D.: Parallel Prefix Sum (Scan) in CUDA. Chapter 39 – GPU Gems 3 (2008)Google Scholar
  14. 14.
    NVIDIA Tegra Developer Zone,

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Thuy Tuong Nguyen
    • 1
  • Jae Wook Jeon
    • 1
  1. 1.School of Information and Communication EngineeringSungkyunkwan UniversitySuwonKorea

Personalised recommendations