论文标题
与图神经网络的联合对象检测和多对象跟踪
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks
论文作者
论文摘要
对象检测和数据关联是多对象跟踪（MOT）系统中的关键组件。尽管这两个组件彼此依赖，但先前的作品通常设计检测和数据关联模块，这些模块是通过单独的目标训练的。结果，一个人不能后退梯度并优化整个MOT系统，从而导致次优性能。为了解决这个问题，最近的工作同时优化了联合MOT框架下的检测和数据关联模块，该模块在两个模块中均显示出改进的性能。在这项工作中，我们提出了一种基于图神经网络（GNN）的联合MOT方法的新实例。关键的想法是，GNN可以在空间和时间域中的可变大小对象之间建模关系，这对于学习检测和数据关联的区分特征至关重要。通过对MOT15/16/17/20数据集的广泛实验，我们证明了基于GNN的关节方法的有效性，并显示了检测和MOT任务的最新性能。我们的代码可在以下网址找到：https：//github.com/yongxinw/gsdt
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 data association modules separately which are trained with separate objectives. As a result, one cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent works simultaneously optimize detection and data association modules under a joint MOT framework, which has shown improved performance in both modules. In this work, we propose a new instance of joint MOT approach based on Graph Neural Networks (GNNs). The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association. Through extensive experiments on the MOT15/16/17/20 datasets, we demonstrate the effectiveness of our GNN-based joint MOT approach and show state-of-the-art performance for both detection and MOT tasks. Our code is available at: https://github.com/yongxinw/GSDT
