Vision-Based Traffic Accident Detection and Anticipation: A Survey

TL;DR

This survey reviews recent advances in vision-based traffic accident detection and anticipation, highlighting challenges, benchmarks, and future research directions in this critical area of road safety.

Contribution

It is the first comprehensive survey on Vision-TAD and Vision-TAA, analyzing existing methods, benchmarks, and evaluation metrics to guide future research.

Findings

Analysis of 31 benchmarks and evaluation metrics

Discussion of pros and cons of current research prototypes

Identification of future research directions in Vision-TAD and Vision-TAA

Abstract

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.