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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yucheng, Emura, Koichi, Watanabe, Eiji
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916508930670592
author Zhang, Yucheng
Emura, Koichi
Watanabe, Eiji
author_facet Zhang, Yucheng
Emura, Koichi
Watanabe, Eiji
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03903
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using SlowFast Networks for Near-Miss Incident Analysis in Dashcam Videos
Zhang, Yucheng
Emura, Koichi
Watanabe, Eiji
Artificial Intelligence
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.
title Using SlowFast Networks for Near-Miss Incident Analysis in Dashcam Videos
topic Artificial Intelligence
url https://arxiv.org/abs/2412.03903