TL;DR本研究提出一种基于图神经网络的联合多目标跟踪方法,通过优化检测和数据关联模块,兼顾准确性和运行效率,成功在多个 MOT 数据集上实现了最先进的性能表现。
Abstract
object detection and data association are critical components in multi-object
tracking (MOT) systems. Despite the fact that the two components are dependent
on each other, prior works often design detection and <