Cargando…

Traffic lights detection and tracking for HD map creation

HD-maps are one of the core components of the self-driving pipeline. Despite the effort of many companies to develop a completely independent vehicle, many state-of-the-art solutions rely on high-definition maps of the environment for localization and navigation. Nevertheless, the creation process o...

Descripción completa

Detalles Bibliográficos
Autores principales: Mentasti, Simone, Simsek, Yusuf Can, Matteucci, Matteo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10020491/
https://www.ncbi.nlm.nih.gov/pubmed/36936409
http://dx.doi.org/10.3389/frobt.2023.1065394
_version_ 1784908267960401920
author Mentasti, Simone
Simsek, Yusuf Can
Matteucci, Matteo
author_facet Mentasti, Simone
Simsek, Yusuf Can
Matteucci, Matteo
author_sort Mentasti, Simone
collection PubMed
description HD-maps are one of the core components of the self-driving pipeline. Despite the effort of many companies to develop a completely independent vehicle, many state-of-the-art solutions rely on high-definition maps of the environment for localization and navigation. Nevertheless, the creation process of such maps can be complex and error-prone or expensive if performed via ad-hoc surveys. For this reason, robust automated solutions are required. One fundamental component of an high-definition map is traffic lights. In particular, traffic light detection has been a well-known problem in the autonomous driving field. Still, the focus has always been on the light state, not the features (i.e., shape, orientation, pictogram). This work presents a pipeline for lights HD-map creation designed to provide accurate georeferenced position and description of all traffic lights seen by a camera mounted on a surveying vehicle. Our algorithm considers consecutive detection of the same light and uses Kalman filtering techniques to provide each target’s smoother and more precise position. Our pipeline has been validated for the detection and mapping task using the state-of-the-art dataset DriveU Traffic Light Dataset. The results show that our model is robust even with noisy GPS data. Moreover, for the detection task, we highlight how our model can correctly identify even far-away targets which are not labeled in the original dataset.
format Online
Article
Text
id pubmed-10020491
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-100204912023-03-18 Traffic lights detection and tracking for HD map creation Mentasti, Simone Simsek, Yusuf Can Matteucci, Matteo Front Robot AI Robotics and AI HD-maps are one of the core components of the self-driving pipeline. Despite the effort of many companies to develop a completely independent vehicle, many state-of-the-art solutions rely on high-definition maps of the environment for localization and navigation. Nevertheless, the creation process of such maps can be complex and error-prone or expensive if performed via ad-hoc surveys. For this reason, robust automated solutions are required. One fundamental component of an high-definition map is traffic lights. In particular, traffic light detection has been a well-known problem in the autonomous driving field. Still, the focus has always been on the light state, not the features (i.e., shape, orientation, pictogram). This work presents a pipeline for lights HD-map creation designed to provide accurate georeferenced position and description of all traffic lights seen by a camera mounted on a surveying vehicle. Our algorithm considers consecutive detection of the same light and uses Kalman filtering techniques to provide each target’s smoother and more precise position. Our pipeline has been validated for the detection and mapping task using the state-of-the-art dataset DriveU Traffic Light Dataset. The results show that our model is robust even with noisy GPS data. Moreover, for the detection task, we highlight how our model can correctly identify even far-away targets which are not labeled in the original dataset. Frontiers Media S.A. 2023-03-03 /pmc/articles/PMC10020491/ /pubmed/36936409 http://dx.doi.org/10.3389/frobt.2023.1065394 Text en Copyright © 2023 Mentasti, Simsek and Matteucci. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Robotics and AI
Mentasti, Simone
Simsek, Yusuf Can
Matteucci, Matteo
Traffic lights detection and tracking for HD map creation
title Traffic lights detection and tracking for HD map creation
title_full Traffic lights detection and tracking for HD map creation
title_fullStr Traffic lights detection and tracking for HD map creation
title_full_unstemmed Traffic lights detection and tracking for HD map creation
title_short Traffic lights detection and tracking for HD map creation
title_sort traffic lights detection and tracking for hd map creation
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10020491/
https://www.ncbi.nlm.nih.gov/pubmed/36936409
http://dx.doi.org/10.3389/frobt.2023.1065394
work_keys_str_mv AT mentastisimone trafficlightsdetectionandtrackingforhdmapcreation
AT simsekyusufcan trafficlightsdetectionandtrackingforhdmapcreation
AT matteuccimatteo trafficlightsdetectionandtrackingforhdmapcreation