Using Sensor Fusion and Machine Learning to Distinguish Pedestrians in Artificial Intelligence-Enhanced Crosswalks - Artificial Intelligence-Enhanced Crosswalks

Aug 5, 2026

Pedestrian safety remains a major urban challenge, especially at crosswalks where accidents frequently occur. This research proposes an intelligent crosswalk that detects pedestrians and vehicles using sensor fusion and machine learning, then triggers an active warning light to alert nearby road users. The system combines radio detection and ranging data with a magnetic field sensor via a hierarchical classifier, using one-class support vector machines for object classification and fuzzy logic to filter magnetic targets. It also introduces a road-signaling fabrication method and validates performance through standardized mechanical, optical, and electrical tests, achieving 99.11% accuracy with 0.0% false positives and improving pedestrian behavior and reducing driver speed.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Background on road signaling and pedestrian safety

Related work and existing crosswalk warning solutions

electronics Article Using Sensor Fusion and Machine Learning to Distinguish Pedestrians in Artiﬁcial Intelligence-Enhanced Crosswalks Jos² Manuel Lozano Dom½nguez , Manuel Joaqu½n Redondo Gonz¡lez, Jose Miguel Davila Martin and Tom¡s de J. Mateo Sanguino * Citation: Lozano Domínguez, J.M.; Redondo González, M.J.; Davila Martin, J.M.; Mateo Sanguino, T.d.J. Using Sensor Fusion and Machine Learning to Distinguish Pedestriansin Artiﬁcial Intelligence-Enhanced Crosswalks. Electronics 2023, 12, 4718 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)electronics12234718 Academic Editor: Praveen Kumar Donta Received: 6 November 2023 Revised: 15 November 2023 Accepted: 16 November 2023 Published: 21 November 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . Department of Electronic Engineering, Computer Systems and Automatics, University of Huelva, Av. de las Artes s/n, 21007 Huelva, Spain; jose.lozano@diesia.uhu.es (J.M.L.D.); redondo@diesia.uhu.es (M.J.R.G.); jmdavila@dimme.uhu.es (J.M.D.M.) * Correspondence: tomas.mateo@diesia.uhu.es; Tel.: +34-959-217665 Abstract: Pedestrian safety is a major concern in urban areas, and crosswalks are one of the most critical locations where accidents can occur. This research introduces an intelligent crosswalk, employing sensor fusion and machine learning techniques to distinguish the presence of pedestrians and drivers. Upon detecting a pedestrian, the system proactively activates a warning light signal. This approach aims to quickly alert nearby people and mitigate potential dangers, thereby strengthening pedestrian safety. The system integrates data from radio detection and ranging sensors and a magnetic ﬁeld sensor, using a hierarchical classiﬁer. The One-Class support vector machine algorithm is used to classify objects in the radio detection and ranging data, while fuzzy logic is used to ﬁlter out targets from the magnetic ﬁeld sensor. Additionally, this work presents a novel method for the manufacture of the road signaling system, using mixtures of resins, aggregates, and reinforcing ﬁbers that are cold-injected into an aluminum mold. The mechanical, optical, and electrical characteristics were subjected to standardized tests, validating its autonomous operation in real-world conditions. The results revealed the system's effectiveness in detecting pedestrians with a 99.11% accuracy and a 0.0% false-positive rate, marking a substantial improvement over the previous fuzzy logic-based system with an 81.33% accuracy. Attitude testing revealed a signiﬁcant 33.33% reduction in pedestrian erratic behavior and a substantial decrease in driver speed (32.83% during the day and 70.6% during the night) compared to conventional crossings. Consequently, this comprehensive work offers a unique solution to pedestrian safety at crosswalks by showcasing the potential of machine learning techniques, particularly the One-Class support vector machine algorithm, in advancing road safety through precise and reliable pattern recognition. Keywords: machine learning; mechanical analysis; road safety; sensor fusion; support vector machine 1. Introduction On roads—whether part of the State Highway Network or urban streets—certain points require increased attention and reduced speed to prevent trafﬁc accidents [1] . There are very different concepts for this aim in terms of the installation, size, and availability of road signaling systems. At the international level, there are various solutions, such asa sensor barrier that detects pedestrians at a crosswalk entrance/exit and ﬂashes lights to alert drivers [2]; a sidewalk system with a camera t

FAQs

How does the proposed intelligent crosswalk detect pedestrians?

It fuses radio detection and ranging sensor data with a magnetic field sensor, then classifies objects using a hierarchical classifier.

Which algorithms are used for classification and filtering?

One-Class support vector machine is used to classify objects in the radio detection and ranging data, while fuzzy logic filters out targets from the magnetic field sensor.

What performance results does the system achieve?

It detects pedestrians with 99.11% accuracy and 0.0% false-positive rate, improving over a prior fuzzy-logic-based system with 81.33% accuracy.

Aug 5, 2026

Upload by Ava Thompson