Vehicle Detection System for Smart Crosswalks Using Sensors and Machine Learning

Jose Manuel Lozano Dominguez, Faroq Al-Tam, Tomas De J.Mateo Sanguino, Noelia Correia

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

6 Citations (Scopus)

Abstract

Cities are transforming into smart areas thanks to several key technologies involving artificial intelligence (AI), 5G or big data aimed at improving the lives of their inhabitants with new services (e.g., transport systems, including road safety). In this field, the paper describes how to improve vehicle detection through several machine learning techniques applied to smart crosswalks. As a main advantage, this approach avoids readjusting labels in classic fuzzy classifiers that typically depends on the system location and road conditions. To address this, various AI methods were evaluated with data taken from real traffic pertaining to roads in Spain and Portugal. The machine learning techniques were random forest (RF), extremely randomized trees (extra-tree), deep reinforcement learning (DRL), time series forecasting (TSF), multi-layer perceptron (MLP), k-nearest neighbor (KNN) and logistic regression (LR). The results were validated through a receiver operating characteristic (ROC) analysis, obtaining the best performance in RF with a true positive rate (TPR) of 96.82%, false positive rate (FPR) of 1.73% and accuracy (ACC) of 97.85%. This was followed by DRL and TSF, while MLP and LR presented the worst outcomes.

Original languageEnglish
Title of host publication18th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2021
PublisherIEEE Press
Pages984-991
Number of pages8
ISBN (Electronic)9781665414937
DOIs
Publication statusPublished - 21 May 2021
EventSystems, Signals and Devices - Monastir, Tunisia
Duration: 22 Mar 202125 Mar 2021
Conference number: 18

Publication series

Name18th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2021

Conference

ConferenceSystems, Signals and Devices
Abbreviated titleSSD-2021
Country/TerritoryTunisia
CityMonastir
Period22 Mar 202125 Mar 2021

Keywords

  • deep reinforcement learning
  • machine learning
  • Smart road safety
  • time forecasting
  • vehicle detection

Fingerprint

Dive into the research topics of 'Vehicle Detection System for Smart Crosswalks Using Sensors and Machine Learning'. Together they form a unique fingerprint.

Cite this