Using Stochastic Gradient-Descent Scheme in Appearance Model Based Face Tracking

Z. Li, J. Chen, A. Chong, Z. Yu, and N. N. Schraudolph. Using Stochastic Gradient-Descent Scheme in Appearance Model Based Face Tracking. In Proc. Intl. Workshop Multimedia Signal Processing (MMSP), IEEE, Cairns, Australia, 2008.

Download

275.0kB	147.8kB	287.8kB

Abstract

Active appearance model (AAM) has been widely used in face tracking and recognition. However, accuracy and efficiency are always two main challenges with the AAM search. The paper therefore proposes a fast appearance-model based 3D face tracking algorithm to track a face appearance with significant translation, rotation, and scaling activities by using stochastic meta-descent (SMD) optimization scheme to accelerate the appearance model search and to improve the tracking efficiency and accuracy. The proposed algorithm constructs an active face appearance model by using several semantic landmark points extracted from each frame and then processes the appearance model search to approximate the model translating, rotating, and scaling by using the SMD filter to minimize the appearance difference between the current model and the new observation. We compare the results with both a conventional AAM and a Camshift filter and find that our algorithm outperforms both two in terms of efficiency and accuracy in tracking a fast moving, rotating, and scaling face object in a video sequence.

BibTeX Entry

@inproceedings{LiCheChoetal08,
     author = {Zhidong Li and Jing Chen and Adrian Chong
               and Zhenghua Yu and Nicol N. Schraudolph},
      title = {\href{http://nic.schraudolph.org/pubs/LiCheChoetal08.pdf}{
               Using Stochastic Gradient-Descent Scheme
               in Appearance Model Based Face Tracking}},
  booktitle = {Proc.\ Intl.\ Workshop Multimedia Signal Processing (MMSP)},
    address = {Cairns, Australia},
  publisher = {IEEE},
       year =  2008,
   b2h_type = {Other},
  b2h_topic = {>Stochastic Meta-Descent, Computer Vision},
   abstract = {
    Active appearance model (AAM) has been widely used in face
    tracking and recognition. However, accuracy and efficiency are
    always two main challenges with the AAM search.  The paper
    therefore proposes a fast appearance-model based 3D face tracking
    algorithm to track a face appearance with significant translation,
    rotation, and scaling activities by using stochastic meta-descent
    (SMD) optimization scheme to accelerate the appearance model
    search and to improve the tracking efficiency and accuracy. The
    proposed algorithm constructs an active face appearance model
    by using several semantic landmark points extracted from each
    frame and then processes the appearance model search to approximate
    the model translating, rotating, and scaling by using the SMD
    filter to minimize the appearance difference between the current
    model and the new observation. We compare the results with both
    a conventional AAM and a Camshift filter and find that our
    algorithm outperforms both two in terms of efficiency and
    accuracy in tracking a fast moving, rotating, and scaling face
    object in a video sequence.
}}