Tracking Objects with Higher Order Interactions via Delayed Column Generation

[edit]

Shaofei Wang, Steffen Wolf, Charless Fowlkes, Julian Yarkony ;
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:1132-1140, 2017.

Abstract

We study the problem of multi-target tracking and data association in video. We formulate this in terms of selecting a subset of high-quality tracks subject to the constraint that no pair of selected tracks is associated with a common detection (of an object). This objective is equivalent to the classic NP-hard problem of finding a maximum-weight set packing (MWSP) where tracks correspond to sets and is made further difficult since the number of candidate tracks grows exponentially in the number of detections. We present a relaxation of this combinatorial problem that uses a column generation formulation where the pricing problem is solved via dynamic programming to efficiently explore the space of tracks. We employ row generation to tighten the bound in such a way as to preserve efficient inference in the pricing problem. We show the practical utility of this algorithm for pedestrian and particle tracking.

Related Material