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 2308.15985cs.AI
收藏

基于视觉的交通事故检测与预测:综述

Vision-Based Traffic Accident Detection and Anticipation: A Survey

Chang’an University(长安大学);National University of Singapore(新加坡国立大学);National Research University Moscow Power Engineering Institute(国立研究型大学莫斯科动力学院);Xi’an Jiaotong University(西安交通大学);Institute for Infocomm Research(资讯通信研究院)

Jianwu Fang, iahuan Qiao, Jianru Xue, Zhengguo Li

AI总结:

本文首次系统综述基于视觉的交通事故检测与预测,分析其分布外挑战、现有方法优劣及31个基准,为未来研究指明方向。

摘要:

交通事故检测与预测是一个棘手的道路安全问题,人们为此付出了大量努力。随着视频数据的快速增长,基于视觉的交通事故检测与预测(称为Vision-TAD和Vision-TAA)成为安全驾驶和监控安全的最后一英里问题。然而,交通事故的长尾性、不平衡性、高度动态性、复杂性和不确定性构成了Vision-TAD和Vision-TAA的分布外(OOD)特征。当前人工智能的发展可能聚焦于这些OOD但重要的问题。对于Vision-TAD和Vision-TAA,已经完成了哪些工作?未来我们应该关注哪些方向?一份全面的综述至关重要。我们呈现了深度学习时代关于Vision-TAD的首篇综述,以及关于Vision-TAA的首篇综述。在调查过程中,详细讨论了每个研究原型的优缺点。此外,我们还对31个公开可用的基准和相关评估指标进行了批判性审查。通过这篇综述,我们希望为Vision-TAD和Vision-TAA任务带来新的见解并开辟可能的趋势。

英文摘要:

Traffic accident detection and anticipation is an obstinate road safety problem and painstaking efforts have been devoted. With the rapid growth of video data, Vision-based Traffic Accident Detection and Anticipation (named Vision-TAD and Vision-TAA) become the last one-mile problem for safe driving and surveillance safety. However, the long-tailed, unbalanced, highly dynamic, complex, and uncertain properties of traffic accidents form the Out-of-Distribution (OOD) feature for Vision-TAD and Vision-TAA. Current AI development may focus on these OOD but important problems. What has been done for Vision-TAD and Vision-TAA? What direction we should focus on in the future for this problem? A comprehensive survey is important. We present the first survey on Vision-TAD in the deep learning era and the first-ever survey for Vision-TAA. The pros and cons of each research prototype are discussed in detail during the investigation. In addition, we also provide a critical review of 31 publicly available benchmarks and related evaluation metrics. Through this survey, we want to spawn new insights and open possible trends for Vision-TAD and Vision-TAA tasks.

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。

↑