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 2403.01147cs.LGcs.AI
收藏

一种基于生成对抗网络与 Transformer 模型的交通事件检测混合模型

A Hybrid Model for Traffic Incident Detection based on Generative Adversarial Networks and Transformer Model

University of Shanghai for Science and Technology(上海理工大学);Capital One(第一资本)

Xinying Lu, Doudou Zhang, Jianli Xiao

AI总结:

针对交通事件检测中数据获取困难与类别不平衡问题,提出融合 Transformer 和 GANs 的混合模型,并在四个真实数据集上验证其检测性能提升。

摘要:

除了提升交通安全并促进快速应急响应外,交通事件检测还通过提供实时交通状态信息,在智能交通系统中发挥着不可或缺的作用,从而使智能交通控制与管理得以实现。以往研究已经发现,除采用先进算法模型外,检测效果还显著受到获取大型数据集以及解决数据集不平衡问题的影响。为应对这些挑战,本文提出一种结合 Transformer 与生成对抗网络(GANs)的混合模型。研究在四个真实数据集上进行实验,以验证 Transformer 在交通事件检测中的优越性。此外,利用 GANs 扩充数据集,并实现 1:4、2:3 和 1:1 的均衡比例。所提模型与基线模型进行了评估比较。结果表明,所提模型增大了数据集规模、平衡了数据集,并在多个方面提升了交通事件检测性能。

英文摘要:

In addition to enhancing traffic safety and facilitating prompt emergency response, traffic incident detection plays an indispensable role in intelligent transportation systems by providing real-time traffic status information. This enables the realization of intelligent traffic control and management. Previous research has identified that apart from employing advanced algorithmic models, the effectiveness of detection is also significantly influenced by challenges related to acquiring large datasets and addressing dataset imbalances. A hybrid model combining transformer and generative adversarial networks (GANs) is proposed to address these challenges. Experiments are conducted on four real datasets to validate the superiority of the transformer in traffic incident detection. Additionally, GANs are utilized to expand the dataset and achieve a balanced ratio of 1:4, 2:3, and 1:1. The proposed model is evaluated against the baseline model. The results demonstrate that the proposed model enhances the dataset size, balances the dataset, and improves the performance of traffic incident detection in various aspects.

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。

↑