Multi Target Tracking by Learning from Generalized Graph Differences
This addresses multi-object tracking for computer vision applications, but it is incremental as it builds on existing network flow formulations with a new training approach.
The paper tackles the problem of learning weights for network flow optimization in multi-object tracking by separating it into an embedding of feasible solutions and an optimization problem, achieving competitive results on the DukeMTMCT dataset.
Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. In this paper an efficient way of learning the weights of such a network is presented. It separates the problem into one embedding of feasible solutions into a one dimensional feature space and one optimization problem. The embedding can be learned using standard SGD type optimization without relying on an additional optimizations within each step. Training data is produced by performing small perturbations of ground truth tracks and representing them using generalized graph differences, which is an efficient way introduced to represent the difference between two graphs. The proposed method is evaluated on DukeMTMCT with competitive results.