sing 
del. 
will 
ons, 
edit 
letic 
their 
ares 
sprit 
Fua, Pascal 
  
  
(c) : A 
Figure 12: Upper body results. (a) Original sequence. (b, c) The final results after one tracking run to roughly adjust 
the posture and a fitting run to refine the skeleton and metaball proportions and the posture. The center row (b) depicts a 
discreet visualization of the metaballs and the bottom row (c) shows the smoothly rendered implicit surface. 
REFERENCES 
Beardsley, P. A., Zissermam, A. and Murray, D. W., 1997. Sequential update of projective and affine structure from 
motion. International Journal of Computer Vision 23(3), pp. 235-259. 
Blanz, V. and Vetter, T., 1999. A Morphable Model for The Synthesis of 3-D Faces. In: Computer Graphics, SIGGRAPH 
Proceedings, Los Angeles, CA, pp. 71-78. 
Bregler, C. and Malik, J., 1998. Tracking people with twists and exponential maps. Conference on Computer Vision and 
Pattern Recognition. 
D' Apuzzo, N., Gruen, A., Plánkers, R. and Fua, P., 2000. Least Squares Matching Tracking Algorithm for Human Body 
Modeling. In: XIX ISPRS Congress, Amsterdam, Netherlands. 
D' Apuzzo, N., Plánkers, R., Fua, P., Gruen, A. and Thalmann, D., 1999. Modeling Human Bodies from Video Sequences. 
In: Electronic Imaging, SPIE Photonics West Symposium, San Jose, CA. 
DeCarlo, D. and Metaxas, D., 1998. Deformable Model-Based Shape and Motion Analysis from Images using Motion 
Residual Error. In: International Conference on Computer Vision, Bombay, India, pp. 113-119. 
Faugeras, O. and Robert, L., 1996. What can two images tell us about a third one? International Journal of Computer 
Vision (18), pp. 5-19. 
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B5. Amsterdam 2000. 267