Cargando…

Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion

It is challenging to achieve robust lane detection based on a single frame, particularly when complicated driving scenarios are present. A novel approach based on multiple frames is proposed in this paper by taking advantage of the fusion of vision and Inertial Measurement Units (IMU). Hough space i...

Descripción completa

Detalles Bibliográficos
Autores principales: Sun, Yi, Li, Jian, Sun, Zhenping
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6566706/
https://www.ncbi.nlm.nih.gov/pubmed/31109121
http://dx.doi.org/10.3390/s19102305
_version_ 1783426909932093440
author Sun, Yi
Li, Jian
Sun, Zhenping
author_facet Sun, Yi
Li, Jian
Sun, Zhenping
author_sort Sun, Yi
collection PubMed
description It is challenging to achieve robust lane detection based on a single frame, particularly when complicated driving scenarios are present. A novel approach based on multiple frames is proposed in this paper by taking advantage of the fusion of vision and Inertial Measurement Units (IMU). Hough space is employed as a storage medium where lane markings can be stored and visited conveniently. The detection of lane markings is achieved by the following steps. Firstly, primary line segments are extracted from a basic Hough space, which is calculated by Hough Transform. Secondly, a CNN-based classifier is introduced to measure the confidence probability of each line segment, and transforms the basic Hough space into a probabilistic Hough space. In the third step, pose information provided by the IMU is applied to align previous probabilistic Hough spaces to the current one and a filtered probabilistic Hough space is acquired by smoothing the primary probabilistic Hough space across frames. Finally, valid line segments with probability higher than 0.7 are extracted from the filtered probabilistic Hough space. The proposed approach is applied experimentally, and the results demonstrate a satisfying performance compared to various existing methods.
format Online
Article
Text
id pubmed-6566706
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-65667062019-06-17 Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion Sun, Yi Li, Jian Sun, Zhenping Sensors (Basel) Article It is challenging to achieve robust lane detection based on a single frame, particularly when complicated driving scenarios are present. A novel approach based on multiple frames is proposed in this paper by taking advantage of the fusion of vision and Inertial Measurement Units (IMU). Hough space is employed as a storage medium where lane markings can be stored and visited conveniently. The detection of lane markings is achieved by the following steps. Firstly, primary line segments are extracted from a basic Hough space, which is calculated by Hough Transform. Secondly, a CNN-based classifier is introduced to measure the confidence probability of each line segment, and transforms the basic Hough space into a probabilistic Hough space. In the third step, pose information provided by the IMU is applied to align previous probabilistic Hough spaces to the current one and a filtered probabilistic Hough space is acquired by smoothing the primary probabilistic Hough space across frames. Finally, valid line segments with probability higher than 0.7 are extracted from the filtered probabilistic Hough space. The proposed approach is applied experimentally, and the results demonstrate a satisfying performance compared to various existing methods. MDPI 2019-05-19 /pmc/articles/PMC6566706/ /pubmed/31109121 http://dx.doi.org/10.3390/s19102305 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sun, Yi
Li, Jian
Sun, Zhenping
Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title_full Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title_fullStr Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title_full_unstemmed Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title_short Multi-Stage Hough Space Calculation for Lane Markings Detection via IMU and Vision Fusion
title_sort multi-stage hough space calculation for lane markings detection via imu and vision fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6566706/
https://www.ncbi.nlm.nih.gov/pubmed/31109121
http://dx.doi.org/10.3390/s19102305
work_keys_str_mv AT sunyi multistagehoughspacecalculationforlanemarkingsdetectionviaimuandvisionfusion
AT lijian multistagehoughspacecalculationforlanemarkingsdetectionviaimuandvisionfusion
AT sunzhenping multistagehoughspacecalculationforlanemarkingsdetectionviaimuandvisionfusion