arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.08857cs.LG
收藏

基于Transformer的多目标密度深度融合

Deep Fusion of Multi-Object Densities Using Transformer

Chalmers University of Technology(查尔姆斯理工大学)

Lechi Li, Chen Dai, Yuxuan Xia, Lennart Svensson

摘要:

在本文中,我们证明了基于深度学习的方法可以用于融合多对象密度。给定一个场景,几个传感器可能具有不同的视场,跟踪本地执行每个传感器的跟踪器,它产生随机有限集多目标密度。为了融合来自不同跟踪器的输出,我们采用了最近提出的基于变换的多对象跟踪器,其中融合结果是全局多对象密度,描述了当前所有活动对象的集合。我们使用合成数据在几个模拟场景中使用不同的参数设置,比较了基于变换的融合方法与性能良好的基于模型的贝叶斯融合方法的性能。仿真结果表明,基于变换的融合方法优于基于模型的贝叶斯方法在我们的实验场景。

英文摘要:

In this paper, we demonstrate that deep learning based method can be used to fuse multi-object densities. Given a scenario with several sensors with possibly different field-of-views, tracking is performed locally in each sensor by a tracker, which produces random finite set multi-object densities. To fuse outputs from different trackers, we adapt a recently proposed transformer-based multi-object tracker, where the fusion result is a global multi-object density, describing the set of all alive objects at the current time. We compare the performance of the transformer-based fusion method with a well-performing model-based Bayesian fusion method in several simulated scenarios with different parameter settings using synthetic data. The simulation results show that the transformer-based fusion method outperforms the model-based Bayesian method in our experimental scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑