论文标题
3D多对象跟踪的图形神经网络
Graph Neural Networks for 3D Multi-Object Tracking
论文作者
论文摘要
3D多对象跟踪（MOT）对自主系统至关重要。最近的工作经常使用逐探管道，在其中独立提取每个对象的特征以计算亲和力矩阵。然后，亲和力矩阵传递给匈牙利算法以进行数据关联。该管道的一个关键过程是学习不同对象的判别特征，以减少数据关联期间的混淆。为此，我们提出了两种创新的技术：（1）我们没有通过引入图形神经网络来独立获得每个对象的特征，而是提出了一种新颖的特征交互机制； （2）我们没有像先前的工作那样从2D或3D空间获得特征，而是提出了一种新型的关节提取器，以学习2D和3D空间的外观和运动特征。通过在KITTI数据集上的实验，我们提出的方法实现了最新的3D MOT性能。我们的项目网站位于http://www.xinshuoweng.com/projects/gnn3dmot。
3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work often uses a tracking-by-detection pipeline, where the feature of each object is extracted independently to compute an affinity matrix. Then, the affinity matrix is passed to the Hungarian algorithm for data association. A key process of this pipeline is to learn discriminative features for different objects in order to reduce confusion during data association. To that end, we propose two innovative techniques: (1) instead of obtaining the features for each object independently, we propose a novel feature interaction mechanism by introducing Graph Neural Networks; (2) instead of obtaining the features from either 2D or 3D space as in prior work, we propose a novel joint feature extractor to learn appearance and motion features from 2D and 3D space. Through experiments on the KITTI dataset, our proposed method achieves state-of-the-art 3D MOT performance. Our project website is at http://www.xinshuoweng.com/projects/GNN3DMOT.
