作者
Asad A Butt, Robert T Collins
发表日期
2013
研讨会论文
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
页码范围
1846-1853
简介
We propose a method for global multi-target tracking that can incorporate higher-order track smoothness constraints such as constant velocity. Our problem formulation readily lends itself to path estimation in a trellis graph, but unlike previous methods, each node in our network represents a candidate pair of matching observations between consecutive frames. Extra constraints on binary flow variables in the graph result in a problem that can no longer be solved by min-cost network flow. We therefore propose an iterative solution method that relaxes these extra constraints using Lagrangian relaxation, resulting in a series of problems that ARE solvable by min-cost flow, and that progressively improve towards a high-quality solution to our original optimization problem. We present experimental results showing that our method outperforms the standard network-flow formulation as well as other recent algorithms that attempt to incorporate higher-order smoothness constraints.
学术搜索中的文章
AA Butt, RT Collins - Proceedings of the IEEE Conference on Computer …, 2013