TY - JOUR
T1 - A fast 2D shape recovery approach by fusing features and appearance
AU - Zhu, Jianke
AU - Lyu, Michael R.
AU - Huang, Thomas S.
N1 - Funding Information:
The authors appreciate the reviewers for their extensive and informative comments for the improvement of this manuscript. Also, the authors would like to thank Dr. Guangyu Wang and Mr. Xiaopei Liu for their fruitful discussions on the GPU programming. The work was fully supported by two Hong Kong Government grants: the Innovation and Technology Fund (ITS/084/07) and the Research Grants Council Earmarked Grant (CUHK4150/07E). The short version of this paper appeared in our previous work published in the Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).
PY - 2009
Y1 - 2009
N2 - In this paper, we present a fusion approach to solve the nonrigid shape recovery problem, which takes advantage of both the appearance information and the local features. We have two major contributions. First, we propose a novel progressive finite Newton optimization scheme for the feature-based nonrigid surface detection problem, which is reduced to only solving a set of linear equations. The key is to formulate the nonrigid surface detection as an unconstrained quadratic optimization problem that has a closed-form solution for a given set of observations. Second, we propose a deformable Lucas-Kanade algorithm that triangulates the template image into small patches and constrains the deformation through the second-order derivatives of the mesh vertices. We formulate it into a sparse regularized least squares problem, which is able to reduce the computational cost and the memory requirement. The inverse compositional algorithm is applied to efficiently solve the optimization problem. We have conducted extensive experiments for performance evaluation on various environments, whose promising results show that the proposed algorithm is both efficient and effective.
AB - In this paper, we present a fusion approach to solve the nonrigid shape recovery problem, which takes advantage of both the appearance information and the local features. We have two major contributions. First, we propose a novel progressive finite Newton optimization scheme for the feature-based nonrigid surface detection problem, which is reduced to only solving a set of linear equations. The key is to formulate the nonrigid surface detection as an unconstrained quadratic optimization problem that has a closed-form solution for a given set of observations. Second, we propose a deformable Lucas-Kanade algorithm that triangulates the template image into small patches and constrains the deformation through the second-order derivatives of the mesh vertices. We formulate it into a sparse regularized least squares problem, which is able to reduce the computational cost and the memory requirement. The inverse compositional algorithm is applied to efficiently solve the optimization problem. We have conducted extensive experiments for performance evaluation on various environments, whose promising results show that the proposed algorithm is both efficient and effective.
KW - Image processing and computer vision
KW - Medical image registration
KW - Nonrigid augmented reality
KW - Nonrigid detection
KW - Real-time deformable registration
UR - http://www.scopus.com/inward/record.url?scp=67349158687&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67349158687&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2008.151
DO - 10.1109/TPAMI.2008.151
M3 - Article
C2 - 19443920
AN - SCOPUS:67349158687
VL - 31
SP - 1210
EP - 1224
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 7
ER -