Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant

Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for prac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Dong-Gyu Lee
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	drivable area estimation autonomous driving multi-task learning lane line detection scene classification real-time processing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/dfa92dd84db34a83bf1cc1767ef068fb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dfa92dd84db34a83bf1cc1767ef068fb
record_format	dspace
spelling	oai:doaj.org-article:dfa92dd84db34a83bf1cc1767ef068fb2021-11-25T16:36:07ZFast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant10.3390/app1122107132076-3417https://doaj.org/article/dfa92dd84db34a83bf1cc1767ef068fb2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10713https://doaj.org/toc/2076-3417Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for practical applications. We propose a fast and accurate multi-task learning-based architecture for joint segmentation of drivable area, lane line, and classification of the scene. An encoder–decoder architecture efficiently handles input frames through shared representation. A comprehensive understanding of the driving environment is improved by generalization and regularization from different tasks. The proposed method learns end-to-end through multi-task learning on a very challenging Berkeley Deep Drive dataset and shows its robustness for three tasks in autonomous driving. Experimental results show that the proposed method outperforms other multi-task learning approaches in both speed and accuracy. The computational efficiency of the method was over 93.81 fps at inference, enabling execution in real-time.Dong-Gyu LeeMDPI AGarticledrivable area estimationautonomous drivingmulti-task learninglane line detectionscene classificationreal-time processingTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10713, p 10713 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	drivable area estimation autonomous driving multi-task learning lane line detection scene classification real-time processing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	drivable area estimation autonomous driving multi-task learning lane line detection scene classification real-time processing Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Dong-Gyu Lee Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
description	Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for practical applications. We propose a fast and accurate multi-task learning-based architecture for joint segmentation of drivable area, lane line, and classification of the scene. An encoder–decoder architecture efficiently handles input frames through shared representation. A comprehensive understanding of the driving environment is improved by generalization and regularization from different tasks. The proposed method learns end-to-end through multi-task learning on a very challenging Berkeley Deep Drive dataset and shows its robustness for three tasks in autonomous driving. Experimental results show that the proposed method outperforms other multi-task learning approaches in both speed and accuracy. The computational efficiency of the method was over 93.81 fps at inference, enabling execution in real-time.
format	article
author	Dong-Gyu Lee
author_facet	Dong-Gyu Lee
author_sort	Dong-Gyu Lee
title	Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
title_short	Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
title_full	Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
title_fullStr	Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
title_full_unstemmed	Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant
title_sort	fast drivable areas estimation with multi-task learning for real-time autonomous driving assistant
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dfa92dd84db34a83bf1cc1767ef068fb
work_keys_str_mv	AT donggyulee fastdrivableareasestimationwithmultitasklearningforrealtimeautonomousdrivingassistant
_version_	1718413108263780352

Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant

Ejemplares similares