PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Multiple Object Tracking using Flow Linear Programming
Jérôme Berclaz, Francois Fleuret and Pascal Fua
In: PETS 2009(2009).

Abstract

Multi-object tracking can be achieved by detecting objects in individual frames and then linking detections across frames. Such an approach can be made very robust to the occasional detection failure: If an object is not detected in a frame but is in previous and following ones, a correct trajectory will nevertheless be produced. By contrast, a false-positive detection in a few frames will be ignored. However, when dealing with a multiple target problem, the linking step results in a difficult optimization problem in the space of all possible families of trajectories. This is usually dealt with by sampling or greedy search based on variants of Dynamic Programming, which can easily miss the global optimum. In this paper, we show that reformulating that step as a constrained flow optimization problem results in a convex problem that can be solved using standard Linear Programming techniques. In addition, this new approach is far simpler formally and algorithmically than existing techniques and yields excellent results on the PETS 2009 data set.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:7329
Deposited By:Francois Fleuret
Deposited On:17 March 2011