Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane

Although numerous road segmentation studies have utilized vision data, obtaining robust classification is still challenging due to vision sensor noise and target object deformation. Long-distance images are still problematic because of blur and low resolution, and these features make distinguishing...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Byeongjun Yu, Dongkyu Lee, Jae-Seol Lee, Seok-Cheol Kee
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	autonomous vehicle bird’s eye view transformation convolutional neural network heterogeneous sensor fusion road detection semantic segmentation Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/6a374b9731d0449ebff8b0f42cd979a4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6a374b9731d0449ebff8b0f42cd979a4
record_format	dspace
spelling	oai:doaj.org-article:6a374b9731d0449ebff8b0f42cd979a42021-11-25T18:58:00ZFree Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane10.3390/s212276231424-8220https://doaj.org/article/6a374b9731d0449ebff8b0f42cd979a42021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7623https://doaj.org/toc/1424-8220Although numerous road segmentation studies have utilized vision data, obtaining robust classification is still challenging due to vision sensor noise and target object deformation. Long-distance images are still problematic because of blur and low resolution, and these features make distinguishing roads from objects difficult. This study utilizes light detection and ranging (LiDAR), which generates information that camera images lack, such as distance, height, and intensity, as a reliable supplement to address this problem. In contrast to conventional approaches, additional domain transformation to a bird’s eye view space is executed to obtain long-range data with resolutions comparable to those of short-range data. This study proposes a convolutional neural network architecture that processes data transformed to a bird’s eye view plane. The network’s pathways are split into two parts to resolve calibration errors in the transformed image and point cloud. The network, which has modules that operate sequentially at various scaled dilated convolution rates, is designed to quickly and accurately handle a wide range of data. Comprehensive empirical studies using the Karlsruhe Institute of Technology and Toyota Technological Institute’s (KITTI’s) road detection benchmarks demonstrate that this study’s approach takes advantage of camera and LiDAR information, achieving robust road detection with short runtimes. Our result ranks 22nd in the KITTI’s leaderboard and shows real-time performance.Byeongjun YuDongkyu LeeJae-Seol LeeSeok-Cheol KeeMDPI AGarticleautonomous vehiclebird’s eye view transformationconvolutional neural networkheterogeneous sensor fusionroad detectionsemantic segmentationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7623, p 7623 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autonomous vehicle bird’s eye view transformation convolutional neural network heterogeneous sensor fusion road detection semantic segmentation Chemical technology TP1-1185
spellingShingle	autonomous vehicle bird’s eye view transformation convolutional neural network heterogeneous sensor fusion road detection semantic segmentation Chemical technology TP1-1185 Byeongjun Yu Dongkyu Lee Jae-Seol Lee Seok-Cheol Kee Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
description	Although numerous road segmentation studies have utilized vision data, obtaining robust classification is still challenging due to vision sensor noise and target object deformation. Long-distance images are still problematic because of blur and low resolution, and these features make distinguishing roads from objects difficult. This study utilizes light detection and ranging (LiDAR), which generates information that camera images lack, such as distance, height, and intensity, as a reliable supplement to address this problem. In contrast to conventional approaches, additional domain transformation to a bird’s eye view space is executed to obtain long-range data with resolutions comparable to those of short-range data. This study proposes a convolutional neural network architecture that processes data transformed to a bird’s eye view plane. The network’s pathways are split into two parts to resolve calibration errors in the transformed image and point cloud. The network, which has modules that operate sequentially at various scaled dilated convolution rates, is designed to quickly and accurately handle a wide range of data. Comprehensive empirical studies using the Karlsruhe Institute of Technology and Toyota Technological Institute’s (KITTI’s) road detection benchmarks demonstrate that this study’s approach takes advantage of camera and LiDAR information, achieving robust road detection with short runtimes. Our result ranks 22nd in the KITTI’s leaderboard and shows real-time performance.
format	article
author	Byeongjun Yu Dongkyu Lee Jae-Seol Lee Seok-Cheol Kee
author_facet	Byeongjun Yu Dongkyu Lee Jae-Seol Lee Seok-Cheol Kee
author_sort	Byeongjun Yu
title	Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
title_short	Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
title_full	Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
title_fullStr	Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
title_full_unstemmed	Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane
title_sort	free space detection using camera-lidar fusion in a bird’s eye view plane
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6a374b9731d0449ebff8b0f42cd979a4
work_keys_str_mv	AT byeongjunyu freespacedetectionusingcameralidarfusioninabirdseyeviewplane AT dongkyulee freespacedetectionusingcameralidarfusioninabirdseyeviewplane AT jaeseollee freespacedetectionusingcameralidarfusioninabirdseyeviewplane AT seokcheolkee freespacedetectionusingcameralidarfusioninabirdseyeviewplane
_version_	1718410466565292032

Free Space Detection Using Camera-LiDAR Fusion in a Bird’s Eye View Plane

Ejemplares similares