An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds

In transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes a...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingxu Chen, Qiru Cao, Mingzhuang Hua, Jinyang Liu, Jie Ma, Di Wang, Aoxiang Liu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Systems
Subjects:
Online Access:https://www.mdpi.com/2079-8954/12/11/480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152346927628288
author Jingxu Chen
Qiru Cao
Mingzhuang Hua
Jinyang Liu
Jie Ma
Di Wang
Aoxiang Liu
author_facet Jingxu Chen
Qiru Cao
Mingzhuang Hua
Jinyang Liu
Jie Ma
Di Wang
Aoxiang Liu
author_sort Jingxu Chen
collection DOAJ
description In transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes an autotuning hybrid method with Bayesian optimization for road edge extraction in highway systems. The hybrid method combines the strengths of 2D feature images and 3D spatial characteristics while also automatically tuning the hyperparameter combination using Bayesian optimization. The hyperparameters encompass high and low pixel gradient thresholds, neighborhood radius, and normal vector threshold. Later, the point cloud dataset of national highways in Henan Province, China, is taken as the case study to evaluate the performance of the proposed method against three benchmark methods in two typical road scenarios: straight and curved edges. Experimental results show that the proposed method outperforms the benchmarks in detection quality and accuracy. It can serve as a decision-making tool to complement traditional manual road surveying, enabling efficient and automated road edge extraction in highway systems.
format Article
id doaj-art-6ac17dcead324f68a76359c1ccc1a9cc
institution Kabale University
issn 2079-8954
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Systems
spelling doaj-art-6ac17dcead324f68a76359c1ccc1a9cc2024-11-26T18:23:22ZengMDPI AGSystems2079-89542024-11-01121148010.3390/systems12110480An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point CloudsJingxu Chen0Qiru Cao1Mingzhuang Hua2Jinyang Liu3Jie Ma4Di Wang5Aoxiang Liu6School of Transportation, Southeast University, Nanjing 211189, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaCollege of General Aviation and Flight, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaTransportation Development Center of Henan Province, Zhengzhou 450003, ChinaTransportation Development Center of Henan Province, Zhengzhou 450003, ChinaIn transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes an autotuning hybrid method with Bayesian optimization for road edge extraction in highway systems. The hybrid method combines the strengths of 2D feature images and 3D spatial characteristics while also automatically tuning the hyperparameter combination using Bayesian optimization. The hyperparameters encompass high and low pixel gradient thresholds, neighborhood radius, and normal vector threshold. Later, the point cloud dataset of national highways in Henan Province, China, is taken as the case study to evaluate the performance of the proposed method against three benchmark methods in two typical road scenarios: straight and curved edges. Experimental results show that the proposed method outperforms the benchmarks in detection quality and accuracy. It can serve as a decision-making tool to complement traditional manual road surveying, enabling efficient and automated road edge extraction in highway systems.https://www.mdpi.com/2079-8954/12/11/480highway systemspoint cloudsroad edge extractionBayesian optimizationhyperparameter combination
spellingShingle Jingxu Chen
Qiru Cao
Mingzhuang Hua
Jinyang Liu
Jie Ma
Di Wang
Aoxiang Liu
An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
Systems
highway systems
point clouds
road edge extraction
Bayesian optimization
hyperparameter combination
title An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
title_full An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
title_fullStr An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
title_full_unstemmed An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
title_short An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds
title_sort autotuning hybrid method with bayesian optimization for road edge extraction in highway systems from point clouds
topic highway systems
point clouds
road edge extraction
Bayesian optimization
hyperparameter combination
url https://www.mdpi.com/2079-8954/12/11/480
work_keys_str_mv AT jingxuchen anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT qirucao anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT mingzhuanghua anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT jinyangliu anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT jiema anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT diwang anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT aoxiangliu anautotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT jingxuchen autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT qirucao autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT mingzhuanghua autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT jinyangliu autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT jiema autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT diwang autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds
AT aoxiangliu autotuninghybridmethodwithbayesianoptimizationforroadedgeextractioninhighwaysystemsfrompointclouds