Using SlowFast Networks for Near-Miss Incident Analysis in Dashcam Videos

TL;DR

This paper employs SlowFast neural networks to analyze near-miss traffic incidents in dashcam videos, improving accuracy and offering insights into human visual perception and traffic safety.

Contribution

It introduces a novel application of SlowFast networks for traffic near-miss detection, inspired by human visual pathways, enhancing analysis accuracy and safety insights.

Findings

Significant accuracy improvement in near-miss classification

Insights into human visual perception in traffic scenarios

Potential to reduce traffic accidents through better analysis

Abstract

This paper classifies near-miss traffic videos using the SlowFast deep neural network that mimics the characteristics of the slow and fast visual information processed by two different streams from the M (Magnocellular) and P (Parvocellular) cells of the human brain. The approach significantly improves the accuracy of the traffic near-miss video analysis and presents insights into human visual perception in traffic scenarios. Moreover, it contributes to traffic safety enhancements and provides novel perspectives on the potential cognitive errors in traffic accidents.