arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00439cs.LG
收藏

采用迁移学习方法、在有限真实标注数据下基于 Transformer 的地图匹配模型

Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach

Korea Advanced Institute of Science and Technology(韩国科学技术院);The University of Queensland(昆士兰大学)

Zhixiong Jin, Jiwon Kim, Hwasoo Yeo, Seongjin Choi

AI总结:

本文提出一种结合迁移学习的 Transformer 地图匹配模型,通过生成轨迹预训练与少量真实数据微调降低成本和现实—虚拟差距,并在点与路段层级验证其优于现有模型。

摘要:

在许多基于空间轨迹的应用中,有必要将原始轨迹数据点映射到数字地图中的道路网络上,这通常被称为地图匹配过程。以往大多数地图匹配方法都侧重于使用基于规则的算法来处理地图匹配问题,而本文从数据驱动的视角来考虑地图匹配任务,提出了一种基于深度学习的地图匹配模型。我们利用迁移学习方法构建了一个基于 Transformer 的地图匹配模型。我们生成轨迹数据来预训练 Transformer 模型,随后使用数量有限的真实标注数据对模型进行微调,以最小化模型开发成本并缩小现实到虚拟的差距。研究采用点和路段两个层级上的三项指标(Average Hamming Distance、F-score 和 BLEU)来评估模型性能。结果表明,所提出的模型优于现有模型。此外,我们利用 Transformer 的注意力权重绘制地图匹配过程,并发现模型是如何正确匹配道路路段的。

英文摘要:

In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process. While most previous map-matching methods have focused on using rule-based algorithms to deal with the map-matching problems, in this paper, we consider the map-matching task from the data-driven perspective, proposing a deep learning-based map-matching model. We build a Transformer-based map-matching model with a transfer learning approach. We generate trajectory data to pre-train the Transformer model and then fine-tune the model with a limited number of ground-truth data to minimize the model development cost and reduce the real-to-virtual gap. Three metrics (Average Hamming Distance, F-score, and BLEU) at two levels (point and segment level) are used to evaluate the model performance. The results indicate that the proposed model outperforms existing models. Furthermore, we use the attention weights of the Transformer to plot the map-matching process and find how the model matches the road segments correctly.

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。

↑