This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Real-time Affine Region Tracking and Coplanar Grouping

V. Ferrari, T. Tuytelaars and L. Van Gool
IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition (CVPR'01)
Hawaii, December 2001


We present a novel approach for tracking locally planar regions in an image sequence and their grouping into larger planar surfaces. The tracker recovers the affine transformation of the region and therefore yields reliable point correspondences between frames. Both edges and texture information are exploited in an integrated way, while not re-quiring the complete region's contour. The tracker withstands zoom, out-of-plane rotations, discontinuous motion and changes in illumination conditions while achieving real-time performance for a region. Multiple tracked regions are grouped into disjoint coplanarity classes. We first define a coplanarity score between each pair of regions, based on motion and texture cues. The scores are then analyzed by a clique-partitioning algorithm yielding the coplanarity classes that best fit the data. The method works in the presence of perspective distortions, discontinuous planar surfaces and considerable amounts of measurement noise.

Download in postscript format
Download in pdf format
  author = {V. Ferrari and T. Tuytelaars and L. Van Gool},
  title = {Real-time Affine Region Tracking and Coplanar Grouping},
  booktitle = {IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition (CVPR'01)},
  year = {2001},
  month = {December},
  pages = {226--233},
  volume = {2},
  publisher = {IEEE Computer Society},
  keywords = {tracking, affinely invariant regions}