Linear Scale and Rotation Invariant Matching

TitleLinear Scale and Rotation Invariant Matching
Publication TypeConference Paper
Year of Publication2011
AuthorsJiang, H., Yu S. X., & Martin D. R.
Published inIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume33
Issue7
Page(s)1339-1355
Date Published07/2011
Keywordsaction detection, deformable matching, linear programming, object matching, scale and rotation invariant matching, shape matching
Abstract

Matching visual patterns that appear scaled, rotated and deformed with respect to each other is a challenging problem. We propose a linear formulation that simultaneously matches feature points and estimates global geometrical transformation in a constrained linear space. The linear scheme enables search space reduction based on the lower convex hull property so that the problem size is largely decoupled from the original hard combinatorial problem. Our method therefore can be used to solve large scale problems that involve a very large number of candidate feature points. Without using pre-pruning in the search, this method is more robust in dealing with weak features and clutter. We apply the proposed method to action detection and image matching. Our results on a variety of images and videos demonstrate that our method is accurate, efficient, and robust.

Acknowledgment

This work is supported in part by US National Science
Foundation Grants 0644204 and 1018641

URLhttp://www1.icsi.berkeley.edu/~stellayu/publication/doc/2011matchPAMI.pdf
ICSI Research Group

Vision