Computational Technology Resources - CCC

M. Abdel Karim¹, A. Alazmi² and T. Alhadidi³

¹School of Business and Economics, Vrije Universiteit Amsterdam, Netherland
²Department of Construction Project, Ministry of Public Works of Kuwait, South Surra, Kuwait
³Civil Engineering Department, Al-Ahliyya Amman University, Jordan

doi:10.4203/ccc.11.3.1

M. Abdel Karim, A. Alazmi, T. Alhadidi, "Develop a Street Speed Bump Extraction and Mapping Framework From Street Level Imagery Using Deep Learning", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 3.1, 2025, doi:10.4203/ccc.11.3.1

Keywords: machine learning, street view imagery, GIS, street speed bump, GPS, ground truth formalisation, sustainable road.

Abstract

Developing smart infrastructure needs innovative road detection solutions to monitor road conditions. The location of speed bumps must be carried out by institutions so that they do not cause accidents and have negative consequences for road users. The aim of this research is to define a framework to detect the location of bumps using deep learning. This paper is proposing an automated way to extract, map, and geo-enable street speed bumps from street view imagery. Using machine learning computer vision-based models demonstrated that street view imagery can provide efficient, high-quality, and cost-effective solutions for large-scale mapping of street speed bumps which can be extended to include other street furniture types. The proposed framework demonstrates superior performance in accuracy and coverage metrics. It achieves an average precision score of 0.93.

download the full-text of this paper (PDF, 8 pages, 612 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 11 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING Edited by: P. Iványi, J. Kruis and B.H.V. Topping Paper 3.1 Develop a Street Speed Bump Extraction and Mapping Framework From Street Level Imagery Using Deep Learning M. Abdel Karim¹, A. Alazmi² and T. Alhadidi³ ¹School of Business and Economics, Vrije Universiteit Amsterdam, Netherland ²Department of Construction Project, Ministry of Public Works of Kuwait, South Surra, Kuwait ³Civil Engineering Department, Al-Ahliyya Amman University, Jordan doi:10.4203/ccc.11.3.1 Full Bibliographic Reference for this paper M. Abdel Karim, A. Alazmi, T. Alhadidi, "Develop a Street Speed Bump Extraction and Mapping Framework From Street Level Imagery Using Deep Learning", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 3.1, 2025, doi:10.4203/ccc.11.3.1 Keywords: machine learning, street view imagery, GIS, street speed bump, GPS, ground truth formalisation, sustainable road. Abstract Developing smart infrastructure needs innovative road detection solutions to monitor road conditions. The location of speed bumps must be carried out by institutions so that they do not cause accidents and have negative consequences for road users. The aim of this research is to define a framework to detect the location of bumps using deep learning. This paper is proposing an automated way to extract, map, and geo-enable street speed bumps from street view imagery. Using machine learning computer vision-based models demonstrated that street view imagery can provide efficient, high-quality, and cost-effective solutions for large-scale mapping of street speed bumps which can be extended to include other street furniture types. The proposed framework demonstrates superior performance in accuracy and coverage metrics. It achieves an average precision score of 0.93. download the full-text of this paper (PDF, 8 pages, 612 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions