综述视觉交通事故预测的深度学习方法与未来方向
Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directions
- 梳理147篇研究，分类四类视觉预测方法
- 指出数据少、泛化差、实时性弱等核心挑战
- 推荐多模态融合与自监督学习作为突破方向
交通事故发生预测与检测对提升道路安全至关重要，基于视觉的交通事故预测（Vision-TAA）在深度学习时代展现出巨大潜力。本文综述了147篇近期研究，聚焦监督、无监督及混合深度学习模型在事故预测中的应用，以及真实世界与合成数据集的使用。当前方法主要分为四类：基于图像和视频特征的预测、时空特征预测、场景理解及多模态数据融合。尽管这些方法显示显著前景，但数据稀缺、复杂场景泛化能力有限、实时性能不足等问题仍普遍存在。本文强调未来研究机遇，包括多模态数据融合、自监督学习及Transformer架构的整合，以提升预测精度与可扩展性。通过总结现有进展并识别关键空白，本文为构建鲁棒、自适应的Vision-TAA系统提供基础参考，助力道路安全与交通管理。
原文摘要 · Abstract (English)
Traffic accident prediction and detection are critical for enhancing road safety, and vision-based traffic accident anticipation (Vision-TAA) has emerged as a promising approach in the era of deep learning. This paper reviews 147 recent studies, focusing on the application of supervised, unsupervised, and hybrid deep learning models for accident prediction, alongside the use of real-world and synthetic datasets. Current methodologies are categorized into four key approaches: image and video feature-based prediction, spatio-temporal feature-based prediction, scene understanding, and multi modal data fusion. While these methods demonstrate significant potential, challenges such as data scarcity, limited generalization to complex scenarios, and real-time performance constraints remain prevalent. This review highlights opportunities for future research, including the integration of multi modal data fusion, self-supervised learning, and Transformer-based architectures to enhance prediction accuracy and scalability. By synthesizing existing advancements and identifying critical gaps, this paper provides a foundational reference for developing robust and adaptive Vision-TAA systems, contributing to road safety and traffic management.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。