用图神经网络解决多目标追踪中的排序分配问题，提升精度与效率。
A Graph Neural Network Approach for Solving the Ranked Assignment Problem in Multi-Object Tracking
- 构建二分图模型，用GNN预测最优匹配顺序
- 相比吉布斯采样准确率更高，避免复杂度瓶颈
- 适合需要高精度数据关联的自动驾驶系统
在多目标追踪（MOT）中，将测量值与轨迹关联是保障自动驾驶安全的关键步骤。为应对轨迹假设数量呈指数增长的问题，必须进行截断处理。在δ-广义标签多伯努利（δ-GLMB）滤波器的应用中，这一截断通常涉及排序分配问题，传统方法如穆尔蒂算法或吉布斯采样分别存在复杂度高或精度低的局限。为此，本文提出一种基于图神经网络（GNN）的排序分配预测方法——RAPNet，通过构建二分图建模该问题，利用深度学习的计算能力实现高效求解。实验表明，RAPNet在精度上优于吉布斯采样，同时克服了传统算法的性能瓶颈。
原文摘要 · Abstract (English)
Associating measurements with tracks is a crucial step in Multi-Object Tracking (MOT) to guarantee the safety of autonomous vehicles. To manage the exponentially growing number of track hypotheses, truncation becomes necessary. In the $δ$-Generalized Labeled Multi-Bernoulli ($δ$-GLMB) filter application, this truncation typically involves the ranked assignment problem, solved by Murty's algorithm or the Gibbs sampling approach, both with limitations in terms of complexity or accuracy, respectively. With the motivation to improve these limitations, this paper addresses the ranked assignment problem arising from data association tasks with an approach that employs Graph Neural Networks (GNNs). The proposed Ranked Assignment Prediction Graph Neural Network (RAPNet) uses bipartite graphs to model the problem, harnessing the computational capabilities of deep learning. The conclusive evaluation compares the RAPNet with Murty's algorithm and the Gibbs sampler, showing accuracy improvements compared to the Gibbs sampler.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。