Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset

Road surface detection is important for safely driving autonomous vehicles. This is because the knowledge of road surface conditions, in particular, dry, wet, and snowy surfaces, should be considered for driving control of autonomous vehicles. With the rise of deep learning technology, road surface...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wansik Choi, Jun Heo, Changsun Ahn
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep neural network CycleGAN road surface detection road friction detection Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/b1c8cdc690cc469b98d06b08fed5b90c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b1c8cdc690cc469b98d06b08fed5b90c
record_format	dspace
spelling	oai:doaj.org-article:b1c8cdc690cc469b98d06b08fed5b90c2021-11-25T18:59:10ZDevelopment of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset10.3390/s212277691424-8220https://doaj.org/article/b1c8cdc690cc469b98d06b08fed5b90c2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7769https://doaj.org/toc/1424-8220Road surface detection is important for safely driving autonomous vehicles. This is because the knowledge of road surface conditions, in particular, dry, wet, and snowy surfaces, should be considered for driving control of autonomous vehicles. With the rise of deep learning technology, road surface detection methods using deep neural networks (DNN) have been widely used for developing road surface detection algorithms. To apply DNN in road surface detection, the dataset should be large and well-balanced for accurate and robust performance. However, most of the images of road surfaces obtained through usual data collection processes are not well-balanced. Most of the collected surface images tend to be of dry surfaces because road surface conditions are highly correlated with weather conditions. This could be a challenge in developing road surface detection algorithms. This paper proposes a method to balance the imbalanced dataset using CycleGAN to improve the performance of a road surface detection algorithm. CycleGAN was used to artificially generate images of wet and snow-covered roads. The road surface detection algorithm trained using the CycleGAN-augmented dataset had a better IoU than the method using imbalanced basic datasets. This result shows that CycleGAN-generated images can be used as datasets for road surface detection to improve the performance of DNN, and this method can help make the data acquisition process easy.Wansik ChoiJun HeoChangsun AhnMDPI AGarticledeep neural networkCycleGANroad surface detectionroad friction detectionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7769, p 7769 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep neural network CycleGAN road surface detection road friction detection Chemical technology TP1-1185
spellingShingle	deep neural network CycleGAN road surface detection road friction detection Chemical technology TP1-1185 Wansik Choi Jun Heo Changsun Ahn Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
description	Road surface detection is important for safely driving autonomous vehicles. This is because the knowledge of road surface conditions, in particular, dry, wet, and snowy surfaces, should be considered for driving control of autonomous vehicles. With the rise of deep learning technology, road surface detection methods using deep neural networks (DNN) have been widely used for developing road surface detection algorithms. To apply DNN in road surface detection, the dataset should be large and well-balanced for accurate and robust performance. However, most of the images of road surfaces obtained through usual data collection processes are not well-balanced. Most of the collected surface images tend to be of dry surfaces because road surface conditions are highly correlated with weather conditions. This could be a challenge in developing road surface detection algorithms. This paper proposes a method to balance the imbalanced dataset using CycleGAN to improve the performance of a road surface detection algorithm. CycleGAN was used to artificially generate images of wet and snow-covered roads. The road surface detection algorithm trained using the CycleGAN-augmented dataset had a better IoU than the method using imbalanced basic datasets. This result shows that CycleGAN-generated images can be used as datasets for road surface detection to improve the performance of DNN, and this method can help make the data acquisition process easy.
format	article
author	Wansik Choi Jun Heo Changsun Ahn
author_facet	Wansik Choi Jun Heo Changsun Ahn
author_sort	Wansik Choi
title	Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
title_short	Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
title_full	Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
title_fullStr	Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
title_full_unstemmed	Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset
title_sort	development of road surface detection algorithm using cyclegan-augmented dataset
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b1c8cdc690cc469b98d06b08fed5b90c
work_keys_str_mv	AT wansikchoi developmentofroadsurfacedetectionalgorithmusingcycleganaugmenteddataset AT junheo developmentofroadsurfacedetectionalgorithmusingcycleganaugmenteddataset AT changsunahn developmentofroadsurfacedetectionalgorithmusingcycleganaugmenteddataset
_version_	1718410483401228288

Development of Road Surface Detection Algorithm Using CycleGAN-Augmented Dataset

Ejemplares similares