Using SlowFast Networks for Near-Miss Incident Analysis in Dashcam Videos
This work addresses traffic safety enhancements by providing insights into human perception and potential cognitive errors in accidents, though it appears incremental as it applies an existing method to a specific domain.
The paper tackled the problem of classifying near-miss traffic incidents in dashcam videos by using a SlowFast deep neural network inspired by human visual processing, resulting in significant accuracy improvements for video analysis.
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.