Scale and Rotation Invariant Matching Using Linearly Augmented Trees
Abstract
We propose a novel linearly augmented tree method for
efficient scale and rotation invariant object matching. The
proposed method enforces pairwise matching consistency
defined on trees, and high-order constraints on all the sites
of a template. The pairwise constraints admit arbitrary
metrics while the high-order constraints use L1 norms and
therefore can be linearized. Such a linearly augmented tree
formulation introduces hyperedges and loops into the basic tree structure, but different from a general loopy graph,
its special structure allows us to relax and decompose the
optimization into a sequence of tree matching problems
efficiently solvable by dynamic programming. The proposed
method also works on continuous scale and rotation parameters; we can match with a scale up to any large number
with the same efficiency. Our experiments on ground truth
data and a variety of real images and videos show that the
proposed method is efficient, accurate and reliable.
Paper
Hao Jiang, Tai-Peng Tian and Stan Sclaroff, "Scale and Rotation Invariant Matching Using Linearly Augmented Trees", IEEE Conference on Computer Vision and Pattern Recognition 2011 (CVPR'11).
[PDF]