Review of Accident Detection Methods Using Dashcam Videos for Autonomous Driving Vehicles

The need for a reliable system to detect high-risk incidents in complex settings like roadways, which are infrequent but potentially dangerous, has arisen due to the occurrence of rare hazardous events. This system would empower self-driving cars to function autonomously over extended periods without human involvement. Among these hazardous occurrences, accidents have received the least attention due to their rarity and diverse nature. Recently, dashboard cameras (dashcams) have gained recognition in academic circles as a cost-effective and accessible solution to enhance the safety of autonomous vehicles when handling accidents, since they are now commonly found in most vehicles. This review presents the progression of concepts in this domain, tracing its development from early ideas to cutting-edge techniques. It categorizes these approaches into supervised, self-supervised, and unsupervised learning. Furthermore, the review thoroughly examines evaluation criteria and available datasets, providing a comprehensive comparison of the strengths and limitations of different methods. Ultimately, the review proposes potential avenues for future research in this field.

I. Introduction

In the context of roads and transportation, human behaviour is crucial in ensuring road safety, but predicting it is complicated because it is influenced by interactions with other road users such as vehicles and pedestrians, as well as the surrounding environment. According to statistics in [1] and [2], a significant percentage of accidents are caused by human error. Therefore, it is essential to comprehend these interactions to facilitate the transition to Level 3+ of automation (classified by Society of Automotive Engineers (SAE) [3]), where autonomous vehicles (AV)s must safely control all driving functions.