Revolutionizing emergency vehicle response: a smart traffic management approach with adaptive CNN and hybrid deep learning

This study explores the important problem of urban traffic congestion, focusing on the challenges that emergency vehicles encounter. Existing traffic management systems frequently fail to efficiently prioritize emergency vehicles, relying on costly sensors or manual intervention. To solve these chal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of information technology (Singapore. Online) Jg. 17; H. 3; S. 1793 - 1804
Hauptverfasser: Vikraman, Bindu Puthentharayil, Mahadevan, Vanitha, Jabbar, Rani Fathima
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Singapore Springer Nature Singapore 01.04.2025
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Artificial Intelligence
Artificial neural networks
Classification
Computer Imaging
Computer Science
Datasets
Decision making
Deep learning
Emergency vehicles
Forecasting techniques
Image Processing and Computer Vision
Machine Learning
Management systems
Neural networks
Original Research
Pattern Recognition and Graphics
Roads & highways
Software Engineering
Surveillance
Time series
Traffic congestion
Traffic control
Traffic flow
Traffic management
Traffic surveillance
Transportation planning
Vehicles
Vision
Enhanced walrus optimization
Traffic surveillance
Adaptive faster R-CNN
Stacked autoEncoder
Modified denseNet201
ISSN:2511-2104, 2511-2112
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study explores the important problem of urban traffic congestion, focusing on the challenges that emergency vehicles encounter. Existing traffic management systems frequently fail to efficiently prioritize emergency vehicles, relying on costly sensors or manual intervention. To solve these challenges, this research presents a unique traffic control technique that detects and prioritizes emergency vehicles using images captured by traffic surveillance cameras.This approach involves denoising input traffic images and recognizing vehicles using Adaptive Faster R-CNN (AfR-CNN), which has been optimized with the Enhanced walrus optimization (EWO) algorithm. In addition, a hybrid deep learning model is used to identify emergency vehicles, with Stacked AutoEncoder (SAE) for feature extraction and modified DenseNet201 for classification. The evaluation metrics utilized for comparing with other deep learning techniques include accuracy, precision, recall, and the F-measure. Test results indicate that the proposed emergency vehicle detection model surpasses alternative deep learning algorithms in vehicle classification accuracy, achieving a remarkable accuracy.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-024-02088-2