SuperFloxels: A Mid-level Representation for Video Sequences

Avinash Ravichandran¹, Chaohui Wang¹, Michalis Raptis², and Stefano Soatto¹

¹Vision Lab, UCLA, USA

²Disney Research, Pittsburgh, USA

Abstract. We describe an approach for grouping trajectories extracted from a video that preserves motion discontinuities due, for instance, to occlusions, but not color or intensity boundaries. Our method takes as input trajectories with variable length and onset time, and outputs a membership function as well as an indicator function denoting the exemplar trajectory of each group. This can be used for several applications such as compression, segmentation, and background removal.

LNCS 7585, p. 131 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012