Recognition of vehicle light signals for smart traffic lights

This paper explores the application of machine learning methods for recognizing automobile light signals to enhance smart traffic light systems. For vehicle detection in video footage, the Keras library was employed along with the RetinaNet neural network architecture [1]. The YOLOv8 architecture wa...

Full description

Saved in:
Bibliographic Details
Main Authors: K. S. Kurochka, D. V. Prokopenko, K. A. Panarin
Format: Article
Language:English
Published: Belarusian National Technical University 2025-04-01
Series:Системный анализ и прикладная информатика
Subjects:
Online Access:https://sapi.bntu.by/jour/article/view/727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849242604671074304
author K. S. Kurochka
D. V. Prokopenko
K. A. Panarin
author_facet K. S. Kurochka
D. V. Prokopenko
K. A. Panarin
author_sort K. S. Kurochka
collection DOAJ
description This paper explores the application of machine learning methods for recognizing automobile light signals to enhance smart traffic light systems. For vehicle detection in video footage, the Keras library was employed along with the RetinaNet neural network architecture [1]. The YOLOv8 architecture was used for identifying the status of vehicle headlights and taillights. Data collection, annotation, and model training were conducted using the Roboflow platform. The research resulted in trained model weights capable of recognizing the state of front and rear lights on various vehicle types under different weather conditions. The paper proposes an adaptation of the YOLOv8-based neural network model for recognizing traffic light signals, which can be utilized for both static recognition in photographs and in real-time or video applications.
format Article
id doaj-art-9bfb308559984d14948b78eeec3bf5dd
institution Kabale University
issn 2309-4923
2414-0481
language English
publishDate 2025-04-01
publisher Belarusian National Technical University
record_format Article
series Системный анализ и прикладная информатика
spelling doaj-art-9bfb308559984d14948b78eeec3bf5dd2025-08-20T03:59:47ZengBelarusian National Technical UniversityСистемный анализ и прикладная информатика2309-49232414-04812025-04-0101273110.21122/2309-4923-2025-1-27-31515Recognition of vehicle light signals for smart traffic lightsK. S. Kurochka0D. V. Prokopenko1K. A. Panarin2Sukhoi State Technical University of GomelSukhoi State Technical University of GomelSukhoi State Technical University of GomelThis paper explores the application of machine learning methods for recognizing automobile light signals to enhance smart traffic light systems. For vehicle detection in video footage, the Keras library was employed along with the RetinaNet neural network architecture [1]. The YOLOv8 architecture was used for identifying the status of vehicle headlights and taillights. Data collection, annotation, and model training were conducted using the Roboflow platform. The research resulted in trained model weights capable of recognizing the state of front and rear lights on various vehicle types under different weather conditions. The paper proposes an adaptation of the YOLOv8-based neural network model for recognizing traffic light signals, which can be utilized for both static recognition in photographs and in real-time or video applications.https://sapi.bntu.by/jour/article/view/727smart traffic lightsneural networksimage processingrecognition taskmodel training
spellingShingle K. S. Kurochka
D. V. Prokopenko
K. A. Panarin
Recognition of vehicle light signals for smart traffic lights
Системный анализ и прикладная информатика
smart traffic lights
neural networks
image processing
recognition task
model training
title Recognition of vehicle light signals for smart traffic lights
title_full Recognition of vehicle light signals for smart traffic lights
title_fullStr Recognition of vehicle light signals for smart traffic lights
title_full_unstemmed Recognition of vehicle light signals for smart traffic lights
title_short Recognition of vehicle light signals for smart traffic lights
title_sort recognition of vehicle light signals for smart traffic lights
topic smart traffic lights
neural networks
image processing
recognition task
model training
url https://sapi.bntu.by/jour/article/view/727
work_keys_str_mv AT kskurochka recognitionofvehiclelightsignalsforsmarttrafficlights
AT dvprokopenko recognitionofvehiclelightsignalsforsmarttrafficlights
AT kapanarin recognitionofvehiclelightsignalsforsmarttrafficlights