Deep Learning-Based Pedestrians Controlling System on Zebra Crossing

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: Indrabhan Kurkute, Swapnali Landge, Madhura Ranmale, Vrushali Ghorpade, Shiveswari Nibe
Format: Recurso digital
Published: Zenodo 2025
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901275410432000
author Indrabhan Kurkute, Swapnali Landge, Madhura Ranmale, Vrushali Ghorpade, Shiveswari Nibe
author_facet Indrabhan Kurkute, Swapnali Landge, Madhura Ranmale, Vrushali Ghorpade, Shiveswari Nibe
contents <p>The 'Vision zero' goal represents the apex of the European Commission's road safety plan, and<br>enhancing road safety is seen as a primary objective by governments and transport policymakers across the<br>globe. Due to the greater death rate associated with crashes involving pedestrians, this vulnerable user<br>group has been the focus of increased study. Consequently, there is a growing need for studies that<br>examine pedestrian behavior and the implementation of Intelligent Transport Systems designed to aid<br>pedestrians. Using a Countdown Signal Timer (CST) and some machine learning techniques, this research<br>aims to forecast how pedestrians would behave at crossings. Presenting this case study is an analysis of a<br>simulated environment model intersection with pedestrian traffic lights equipped with countdown signal<br>timings. An X-Convolutional Neural Network (X-CNN) and a decision-making model were both<br>employed to meet the requirements of the analysis. Both models demonstrated satisfactory performance,<br>according to the results. To be more specific, the X-CNN model used a Mean Squared Error value to<br>predict the pedestrians' crossing speed. By accurately predicting how pedestrians cross the street, we may<br>learn more about the impact of countdown signal timers and how to improve infrastructure safety for this<br>demographic so that they receive timely and relevant information through the speaker. </p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15207601
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Deep Learning-Based Pedestrians Controlling System on Zebra Crossing
Indrabhan Kurkute, Swapnali Landge, Madhura Ranmale, Vrushali Ghorpade, Shiveswari Nibe
<p>The 'Vision zero' goal represents the apex of the European Commission's road safety plan, and<br>enhancing road safety is seen as a primary objective by governments and transport policymakers across the<br>globe. Due to the greater death rate associated with crashes involving pedestrians, this vulnerable user<br>group has been the focus of increased study. Consequently, there is a growing need for studies that<br>examine pedestrian behavior and the implementation of Intelligent Transport Systems designed to aid<br>pedestrians. Using a Countdown Signal Timer (CST) and some machine learning techniques, this research<br>aims to forecast how pedestrians would behave at crossings. Presenting this case study is an analysis of a<br>simulated environment model intersection with pedestrian traffic lights equipped with countdown signal<br>timings. An X-Convolutional Neural Network (X-CNN) and a decision-making model were both<br>employed to meet the requirements of the analysis. Both models demonstrated satisfactory performance,<br>according to the results. To be more specific, the X-CNN model used a Mean Squared Error value to<br>predict the pedestrians' crossing speed. By accurately predicting how pedestrians cross the street, we may<br>learn more about the impact of countdown signal timers and how to improve infrastructure safety for this<br>demographic so that they receive timely and relevant information through the speaker. </p>
title Deep Learning-Based Pedestrians Controlling System on Zebra Crossing
url https://doi.org/10.5281/zenodo.15207601