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):

Multi-Scale Clustering of Frame-to-Frame Correspondences for Motion Segmentation

Ralf Dragon, Bodo Rosenhahn and Jörn Ostermann
ECCV 2012
October 2012


In this paper we present an approach for motion segmenta- tion using independently detected keypoints instead of commonly used tracklets or trajectories. This allows us to establish correspondences over non-consecutive frames, thus we are able to handle multiple object oc- clusions consistently. On a frame-to-frame level, we extend the classical split-and-merge algorithm for fast and precise frame-to-frame motion segmentation. Globally, we cluster multiple frame-to-frame motion seg- mentations of different time scales with an accurate estimation of the number of motions. On the standard benchmarks, our approach performs best in comparison to all algorithms which are able to handle missing data. We further show that it works on benchmark data with more than 98% of the input data missing. Finally, we demonstrate the strength of our approach on a challenging mobile-phone-recorded sequence with multiple objects occluded at the same time.

Link to publisher's page
  author = {Ralf Dragon and Bodo Rosenhahn and J\"orn Ostermann},
  title = {Multi-Scale Clustering of Frame-to-Frame Correspondences for Motion Segmentation},
  booktitle = {ECCV 2012},
  year = {2012},
  month = {October},
  keywords = {}