Robust , fast and accurate lane departure warning system using deep learning and mobilenets

Every year, millions of people die from fatalities on the road. This paper develops a lane departure warning system that will alert the driver when the driver may be veering off the road. Recent advances in Deep learning and Artificial Intelligence have shown that Convolutional Neural Networks...

Full description

Bibliographic Details
Main Authors: Olanrewaju, Rashidah Funke, Ahmad Fakhri, Ahmad Syarifuddin, Sanni, Mistura L., Ajala, Mosud Taiwo
Format: Proceeding Paper
Language:English
English
Published: 2019
Subjects:
Online Access:http://irep.iium.edu.my/79642/
http://irep.iium.edu.my/79642/1/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_complete.pdf
http://irep.iium.edu.my/79642/2/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_scopus.pdf
_version_ 1848788806979813376
author Olanrewaju, Rashidah Funke
Ahmad Fakhri, Ahmad Syarifuddin
Sanni, Mistura L.
Ajala, Mosud Taiwo
author_facet Olanrewaju, Rashidah Funke
Ahmad Fakhri, Ahmad Syarifuddin
Sanni, Mistura L.
Ajala, Mosud Taiwo
author_sort Olanrewaju, Rashidah Funke
building IIUM Repository
collection Online Access
description Every year, millions of people die from fatalities on the road. This paper develops a lane departure warning system that will alert the driver when the driver may be veering off the road. Recent advances in Deep learning and Artificial Intelligence have shown that Convolutional Neural Networks can be excellent at extracting and identifying features in an image. However, Convolutional Neural Networks are often run on Expensive GPU’s with colossal memory and typically run millions of operations in a second. This is a challenging problem for embedded characterized by limited memory or processing power and a real-time capability. In this paper, a lightweight, robust and low memory architecture is explored to enable its incorporation as an embedded system. The proposed final architecture utilizes a novel semantic regression technique that integrates the accuracy of semantic segregation and the speed of regression. An end-to-end Deep learning system is used which takes images as an inputs and outputs the found lane in one shot. The developed system achieves 91.83% accuracy on Malaysian roads.
first_indexed 2025-11-14T17:46:41Z
format Proceeding Paper
id iium-79642
institution International Islamic University Malaysia
institution_category Local University
language English
English
last_indexed 2025-11-14T17:46:41Z
publishDate 2019
recordtype eprints
repository_type Digital Repository
spelling iium-796422020-07-15T03:26:01Z http://irep.iium.edu.my/79642/ Robust , fast and accurate lane departure warning system using deep learning and mobilenets Olanrewaju, Rashidah Funke Ahmad Fakhri, Ahmad Syarifuddin Sanni, Mistura L. Ajala, Mosud Taiwo T Technology (General) TK Electrical engineering. Electronics Nuclear engineering Every year, millions of people die from fatalities on the road. This paper develops a lane departure warning system that will alert the driver when the driver may be veering off the road. Recent advances in Deep learning and Artificial Intelligence have shown that Convolutional Neural Networks can be excellent at extracting and identifying features in an image. However, Convolutional Neural Networks are often run on Expensive GPU’s with colossal memory and typically run millions of operations in a second. This is a challenging problem for embedded characterized by limited memory or processing power and a real-time capability. In this paper, a lightweight, robust and low memory architecture is explored to enable its incorporation as an embedded system. The proposed final architecture utilizes a novel semantic regression technique that integrates the accuracy of semantic segregation and the speed of regression. An end-to-end Deep learning system is used which takes images as an inputs and outputs the found lane in one shot. The developed system achieves 91.83% accuracy on Malaysian roads. 2019-10 Proceeding Paper NonPeerReviewed application/pdf en http://irep.iium.edu.my/79642/1/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_complete.pdf application/pdf en http://irep.iium.edu.my/79642/2/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_scopus.pdf Olanrewaju, Rashidah Funke and Ahmad Fakhri, Ahmad Syarifuddin and Sanni, Mistura L. and Ajala, Mosud Taiwo (2019) Robust , fast and accurate lane departure warning system using deep learning and mobilenets. In: "7th International Conference on Mechatronics Engineering, ICOM 2019", 30 - 31 Oct. 2019, Putrajaya, Malaysia. https://ieeexplore-ieee-org.ezproxy.um.edu.my/document/8952067
spellingShingle T Technology (General)
TK Electrical engineering. Electronics Nuclear engineering
Olanrewaju, Rashidah Funke
Ahmad Fakhri, Ahmad Syarifuddin
Sanni, Mistura L.
Ajala, Mosud Taiwo
Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title_full Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title_fullStr Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title_full_unstemmed Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title_short Robust , fast and accurate lane departure warning system using deep learning and mobilenets
title_sort robust , fast and accurate lane departure warning system using deep learning and mobilenets
topic T Technology (General)
TK Electrical engineering. Electronics Nuclear engineering
url http://irep.iium.edu.my/79642/
http://irep.iium.edu.my/79642/
http://irep.iium.edu.my/79642/1/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_complete.pdf
http://irep.iium.edu.my/79642/2/79642_Robust%2C%20Fast%20and%20Accurate%20Lane%20Departure%20_scopus.pdf