Global data association for multi-object tracking using network flows
Global data association for multi-object tracking using network flows
复制标题
DOI：
10.1109/cvpr.2008.4587584
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
Li Zhang;Yuan Li;R. Nevatia
中科院分区：
文献类型：
--
作者：
Li Zhang;Yuan Li;R. Nevatia
我们提出了一种基于网络流的多目标跟踪所需的数据关联优化方法。最大后验概率（MAP）数据关联问题被映射到一个成本流网络与非重叠的轨迹约束。最佳数据关联是通过网络中的最小费用流算法找到的。该网络被增强以包括显式遮挡模型（EOM）来跟踪长期对象间遮挡。基于EOM的网络的解决方案是通过建立在原始算法上的迭代方法找到的。轨迹和潜在的假观测的中断和终止由该公式内在地建模。该方法是有效的，不需要修剪假设。性能与以前的结果进行比较，两个公共行人数据集，以显示其改善。
We propose a network flow based optimization method for data association needed for multiple object tracking. The maximum-a-posteriori (MAP) data association problem is mapped into a cost-flow network with a non-overlap constraint on trajectories. The optimal data association is found by a min-cost flow algorithm in the network. The network is augmented to include an explicit occlusion model(EOM) to track with long-term inter-object occlusions. A solution to the EOM-based network is found by an iterative approach built upon the original algorithm. Initialization and termination of trajectories and potential false observations are modeled by the formulation intrinsically. The method is efficient and does not require hypotheses pruning. Performance is compared with previous results on two public pedestrian datasets to show its improvement.