融合传统模型与神经网络，提升多目标跟踪精度与效率。
A New Architecture for Neural Enhanced Multiobject Tracking
- 设计新神经架构，优化数据关联与新目标初始化
- 在nuScenes LiDAR-only挑战中领先，性能优于现有方法
- 适合需要高精度、低延迟的自动驾驶与机器人场景
多目标跟踪（MOT）在机器人、自动驾驶和海上监视中至关重要。传统方法基于模型，依赖顺序贝叶斯估计；近年方法则完全数据驱动，依赖神经网络训练。两者在不同场景各有优势，尤其在有充足标注数据时，数据驱动方法表现更优。本文推进了近期提出的混合模型-数据驱动方法：神经增强信念传播（NEBP），提出一种新型神经架构，显著改进数据关联与新目标初始化两个关键环节。该方法在提交时已领跑nuScenes LiDAR-only跟踪挑战。
原文摘要 · Abstract (English)
Multiobject tracking (MOT) is an important task in robotics, autonomous driving, and maritime surveillance. Traditional work on MOT is model-based and aims to establish algorithms in the framework of sequential Bayesian estimation. More recent methods are fully data-driven and rely on the training of neural networks. The two approaches have demonstrated advantages in certain scenarios. In particular, in problems where plenty of labeled data for the training of neural networks is available, data-driven MOT tends to have advantages compared to traditional methods. A natural thought is whether a general and efficient framework can integrate the two approaches. This paper advances a recently introduced hybrid model-based and data-driven method called neural-enhanced belief propagation (NEBP). Compared to existing work on NEBP for MOT, it introduces a novel neural architecture that can improve data association and new object initialization, two critical aspects of MOT. The proposed tracking method is leading the nuScenes LiDAR-only tracking challenge at the time of submission of this paper.
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。