Joint Spatial and Tonal Mosaic Alignment for Motion Detection with PTZ Camera

  • Pietro Azzari
  • Alessandro Bevilacqua
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)


Scene segmentation among background and foreground (moving) regions represents the first layer of many applications such as visual surveillance. Exploiting PTZ cameras permits to widen the field of view of a surveyed area and to achieve real object tracking through pan and tilt movements of the observer point of view. Having a mosaiced background allows a system to exploit the background subtraction technique even with moving cameras. Although spatial alignment issues have been thoroughly investigated, tonal registration has been often left out of consideration. This work presents a robust general purpose technique to perform spatial and tonal image registration to achieve a background mosaic without exploiting any prior information regarding the scene or the acquisition device. Accurate experiments accomplished on outdoor and indoor scenes assess the visual quality of the mosaic. Finally, the last experiment proves the effectiveness of using such a mosaic in our visual surveillance application.


Motion Detection Automatic Gain Control Image Mosaic Visual Surveillance Indoor Scene 
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.
    Grundland, M., Dogson, N.A.: Color Histogram Specification by Histogram Warping. In: Proceedings of SPIE (Society of Photo-Optical Instrumentation Engineers) Color Imaging X: Processing, Hardcopy, and Applications, San Jose, CA, January 17-20, 2005, vol. 5667, pp. 610–621 (2005)Google Scholar
  2. 2.
    Mann, S.: ‘Pencigraphy’ with AGC: Joint Parameter Estimation in Both Domain and Range of Functions in Same Orbit of the Projective Wyckoff Group. In: Proceedings of IEEE International Conference on Image Processing, ICIP 1996, vol. 3, pp. 193–196 (September 1996)Google Scholar
  3. 3.
    Mann, S., Manders, C., Fung, J.: Painting with Looks: Photographic Images from Video using Quantimetric Processing. In: Proceedings of ACM Multimedia (2002)Google Scholar
  4. 4.
    Deng, Y., Zhang, T.: Generating Panorama Photos. Hewlett Packard Tech. Report (2003)Google Scholar
  5. 5.
    Mitsunaga, T., Nayar, S.K.: Radiometric Self Calibration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR 1999, Fort Collins, CO, pp. 374–380 (1999)Google Scholar
  6. 6.
    Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs. In: Proceedings of ACM SIGGRAPH 1997, pp. 369–378 (1997)Google Scholar
  7. 7.
    Bevilacqua, A., Di Stefano, L., Azzari, P.: An Effective Real-Time Mosaicing Algorithm Apt to Detect Motion Through Background Subtraction using a PTZ Camera. In: Proceedings of IEEE Conference on Advanced Video and Signal based Surveillance, AVSS 2005, Como, Italy, September 15-16, 2005, vol. 1, pp. 511–516 (2005)Google Scholar
  8. 8.
    Tsin, Y., Ramesh, V., Kanade, T.: Statistical Calibration of CCD Imaging Process. In: Proceedings of IEEE International Conference on Computer Vision, ICCC 2001, vol. 1, pp. 480–487 (2001)Google Scholar
  9. 9.
    Candocia, F.M.: Jointly Registering Images in Domain and Range by Piecewise Linear Comparametric Analysis. IEEE Transactions on Image Processing 12(4) (April 2003)Google Scholar
  10. 10.
    Candocia, F.M., Mandarino, D.A.: A Semiparametric Model for Accurate Camera Response Function Modeling and Exposure from Comparametric Data. IEEE Transactions on Image Processing 14(8) (August 2005)Google Scholar
  11. 11.
    Grossberg, M.D., Nayar, S.K.: Determining the Camera Response Function from Images. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(11) (November 2003)Google Scholar
  12. 12.
    Kropp, A., Master, N., Teller, S.: Acquiring and Rendering High-Resolution Spherical Mosaics. In: Proceedings of IEEE Workshop on OmniDirectional Vision, pp. 47–53 (June 2000)Google Scholar
  13. 13.
    Uyttendaele, M., Eden, A., Szeliski, R.: Eliminating Ghost and Exposure Artifacts in Image Mosaics. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134. Springer, Heidelberg (2001)Google Scholar
  14. 14.
    Bhat, K.S., Saptharishi, M., Khosla, P.K.: Motion Detection and Segmentation Using Image Mosaics. In: Proceedings of IEEE International Conference on Multimedia and Expo., vol. 3, pp. 1577–1580 (July 2000)Google Scholar
  15. 15.
    Capel, D.P.: Image Mosaicing and Super-Resolution. PhD Dissertation Thesis. Robotic Research Group, University of Oxford (2001)Google Scholar
  16. 16.
    Bouguet, J.Y.: Camera Calibration Toolbox for MatlabGoogle Scholar
  17. 17.
    Tomasi, S.: Good Features to Track. In: Proceddings of IEEE Computer Vision and Pattern Recognition, CVPR 1994, pp. 593–600 (1994) Google Scholar
  18. 18.
    Bevilacqua, A., Di Stefano, L., Lanza, A.: An efficient motion detection algorithm based on a statistical non parametric noise model. In: Proceedings of 17th IEEE International Conference on Image Processing (ICIP 2004), Singapore, October 24-27, 2004, pp. 2347–2350 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Pietro Azzari
    • 1
  • Alessandro Bevilacqua
    • 1
  1. 1.ARCES – DEIS (Departments of Electronics, Computer Science and Systems)University of BolognaBolognaItaly

Personalised recommendations