id: 06019267
dt: j
an: 06019267
au: Hofmann, Michael; Gavrila, Dariu M.
ti: 3D human model adaptation by frame selection and shape-texture
    optimization.
so: Comput. Vis. Image Underst. 115, No. 11, 1559-1570 (2011).
py: 2011
pu: Elsevier Science (Academic Press), San Diego, CA
la: EN
cc: 
ut: human motion analysis; 3D articulated pose estimation
ci: 
li: doi:10.1016/j.cviu.2011.08.002
ab: Summary: We present a novel approach for 3D human body shape model
    adaptation to a sequence of multi-view images, given an initial shape
    model and initial pose sequence. In a first step, the most informative
    frames are determined by optimization of an objective function that
    maximizes a shape-texture likelihood function and a pose diversity
    criterion (i.e. the model surface area that lies close to the occluding
    contours), in the selected frames. Thereafter, a batch-mode
    optimization is performed of the underlying shape- and pose-parameters,
    by means of an objective function that includes both contour and
    texture cues over the selected multi-view frames.
rv: