Estimating 3D Facial Shape and Motion from Stereo Image Using Active Appearance Models with Stereo Constraints

  • Jaewon Sung
  • Daijin Kim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)


This paper proposes a new fitting algorithm which we call Stereo Active Appearance Model (STAAM). This algorithm fits a 2D+3D Active Appearance Model to stereo images acquired from calibrated vision system and computes the 3D shape and rigid motion parameters. The use of calibration information reduces the number of model parameters, restricts the degree of freedom in the model parameters, and increases the accuracy and speed of fitting. Moreover, the STAAM uses a modified inverse compositional simultaneous update fitting algorithm to reduce the fitting computation greatly. Experimental results show that (1) the modified inverse compositional simultaneous update algorithm accelerates the AAM fitting speed while keeping its fitting accuracy, (2) the STAAM improves fitting stability using calibration information.


Root Mean Square Hessian Matrix Stereo Image View Image Rigid Transformation 
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.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active Appearance Models. IEEE Trans. on Pattern Recognition and Machine Intelligence 23(6), 681–685 (2001)CrossRefGoogle Scholar
  2. 2.
    Ahlberg, J.: Using the Active Appearance Algorithm for Face and Facial Feature Tracking. In: IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS 2001), p. 68 (2001)Google Scholar
  3. 3.
    Li, Y., Gong, S., Liddell, H.: Modelling Faces Dynamically Across Views and Over Time. In: IEEE International Conference on Computer Vision (2001)Google Scholar
  4. 4.
    Xiao, J., Baker, S., Matthews, I., Kanade, T.: Real-Time Combined 2D+3D Active Appearance Models. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition (January 2004)Google Scholar
  5. 5.
    Hu, C., Xiao, J., Matthews, I., Baker, S., Cohn, J., Kanade, T.: Fitting a Single Active Appearance Model Simultaneously to Multiple Images. In: Proc. of the British Machine Vision Conference (September 2004)Google Scholar
  6. 6.
    Koterba, S., Baker, S., Matthews, I.: Multi-View AAM Fitting and Camera Calibration. In: International Conference on Computer Vision (2005)Google Scholar
  7. 7.
    Matthews, R.G.I., Baker, S.: Lucas-Kanade 20 Years on: A Unifying Framework: Part 3, Cmu-ri-tr-03-05, CMU (November 2003)Google Scholar
  8. 8.
    Matthews, I., Baker, S.: Active Appearance Models Revisited, CMU-RI-TR-03-01, CMU (April 2003)Google Scholar
  9. 9.
    Xiao, J., Kanade, T.: Robust Full-Motion Recovery of Head by Dynamic Templates and Registration Techniques. In: IEEE International Conference on Automatic Face and Gesture Recognition (May 2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jaewon Sung
    • 1
  • Daijin Kim
    • 1
  1. 1.Department of Computer Science and EngineeringPohang University of Science and TechnologyPohangKorea

Personalised recommendations