PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Tracking Multiple Objects under Global Appearance Constraints
Horesh Ben Shitrit, Jerome Berclaz, Francois Fleuret and Pascal Fua
In: IEEE International Conference on Computer Vision(2011).


In this paper, we show that tracking multiple people whose paths may intersect can be formulated as a convex global optimization problem. Our proposed framework is designed to exploit image appearance cues to prevent identity switches. Our method is effective even when such cues are only available at distant time intervals. This is unlike many current approaches that depend on appearance being exploitable from frame to frame. We validate our approach on three multi-camera sport and pedestrian data-sets that contain long and complex sequences. Our algorithm perseveres identities better than state-of-the-art algorithms while keeping similar MOTA scores.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:9368
Deposited By:Francois Fleuret
Deposited On:16 March 2012