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 2011.07728cs.LG
收藏

TLab:基于HR-NET的交通地图视频预测

TLab: Traffic Map Movie Forecasting Based on HR-NET

Purdue University(普渡大学);Southeast Univeristy(东南大学);Chalmers University of Technology(查尔姆斯理工大学)

Fanyou Wu, Yang Liu, Zhiyuan Liu, Xiaobo Qu, Rado Gazo, Eva Haviarova

摘要:

大规模时空交通数据的有效预测问题一直困扰着智能交通领域的研究者。受数据量的限制,目前很少实现全市范围内的交通状态预测。因此,整个城市的复杂的城市交通系统无法真正理解。由于IARAI等组织的努力,他们提供的大量开放数据使研究成为可能。在我们的2020年竞赛解决方案中,我们进一步设计了基于HR-NET和UNet的多种变体。通过特征工程,手工制作的特征以通道的形式输入到模型中。值得注意的是,为了学习地理位置的固有属性,我们提出了一种称为地理嵌入的新方法,该方法有助于显着提高模型的准确性。此外,我们还探讨了激活函数和优化器的选择,以及模型训练过程中的技巧对模型性能的影响。在预测准确性方面,我们的解决方案在NeurIPS 2020年的Quanic 4cast挑战赛中获得了第二名。

英文摘要:

The problem of the effective prediction for large-scale spatio-temporal traffic data has long haunted researchers in the field of intelligent transportation. Limited by the quantity of data, citywide traffic state prediction was seldom achieved. Hence the complex urban transportation system of an entire city cannot be truly understood. Thanks to the efforts of organizations like IARAI, the massive open data provided by them has made the research possible. In our 2020 Competition solution, we further design multiple variants based on HR-NET and UNet. Through feature engineering, the hand-crafted features are input into the model in a form of channels. It is worth noting that, to learn the inherent attributes of geographical locations, we proposed a novel method called geo-embedding, which contributes to significant improvement in the accuracy of the model. In addition, we explored the influence of the selection of activation functions and optimizers, as well as tricks during model training on the model performance. In terms of prediction accuracy, our solution has won 2nd place in NeurIPS 2020, Traffic4cast Challenge.

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。

↑