Machine learning-based optimization of photogrammetric JRC accuracy

Abstract To improve the accuracy of photogrammetric joint roughness coefficient (JRC) estimation, this study proposes two optimization models based on ground sample distance (GSD), point density, and the root mean square error (RMSE) of checkpoints. First, an algorithm that automatically generates s...

Full description

Saved in:
Bibliographic Details
Main Authors: Qinzheng Yang, Ang Li, Yipeng Liu, Hongtian Wang, Zhendong Leng, Fei Deng
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-77054-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061788518809600
author Qinzheng Yang
Ang Li
Yipeng Liu
Hongtian Wang
Zhendong Leng
Fei Deng
author_facet Qinzheng Yang
Ang Li
Yipeng Liu
Hongtian Wang
Zhendong Leng
Fei Deng
author_sort Qinzheng Yang
collection DOAJ
description Abstract To improve the accuracy of photogrammetric joint roughness coefficient (JRC) estimation, this study proposes two optimization models based on ground sample distance (GSD), point density, and the root mean square error (RMSE) of checkpoints. First, an algorithm that automatically generates spatial positions for equipment based on the convergence strategy was developed, using principles of Structure from Motion and Multi-View Stereo (SfM-MVS) and the shooting parameter selection algorithm (SPSA). Second, a portable positioning plate containing ground control points and checkpoints was designed based on optical principles, and a moving camera capture strategy guided by SPSA was proposed. Combining SPSA, portable positioning plate, and moving camera capture strategy, a photogrammetric experiment for small-scale rock samples in the field was conducted, collecting 48 datasets with different shooting parameters. Subsequently, a dataset incorporating GSD, point density, RMSE, and three JRC estimation metrics was established, revealing their correlations and sensitivities. Using seven machine learning algorithms, optimization models for photogrammetric JRC accuracy were developed, with Linear Multidimensional Regression and Gaussian Process Regression models improving JRC accuracy by an average of 85.73%. Finally, the applicability and limitations of the newly proposed method were further discussed.
format Article
id doaj-art-0b2d5432ab3747969b64bfcf654f2383
institution DOAJ
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0b2d5432ab3747969b64bfcf654f23832025-08-20T02:50:06ZengNature PortfolioScientific Reports2045-23222024-11-0114111510.1038/s41598-024-77054-wMachine learning-based optimization of photogrammetric JRC accuracyQinzheng Yang0Ang Li1Yipeng Liu2Hongtian Wang3Zhendong Leng4Fei Deng5School of Highway, Chang’an UniversitySchool of Highway, Chang’an UniversitySchool of Energy and Electrical Engineering, Chang’an UniversitySchool of Highway, Chang’an UniversityChina Gezhouba Group Explosive Co., LtdNorth China Institute of Science and TechnologyAbstract To improve the accuracy of photogrammetric joint roughness coefficient (JRC) estimation, this study proposes two optimization models based on ground sample distance (GSD), point density, and the root mean square error (RMSE) of checkpoints. First, an algorithm that automatically generates spatial positions for equipment based on the convergence strategy was developed, using principles of Structure from Motion and Multi-View Stereo (SfM-MVS) and the shooting parameter selection algorithm (SPSA). Second, a portable positioning plate containing ground control points and checkpoints was designed based on optical principles, and a moving camera capture strategy guided by SPSA was proposed. Combining SPSA, portable positioning plate, and moving camera capture strategy, a photogrammetric experiment for small-scale rock samples in the field was conducted, collecting 48 datasets with different shooting parameters. Subsequently, a dataset incorporating GSD, point density, RMSE, and three JRC estimation metrics was established, revealing their correlations and sensitivities. Using seven machine learning algorithms, optimization models for photogrammetric JRC accuracy were developed, with Linear Multidimensional Regression and Gaussian Process Regression models improving JRC accuracy by an average of 85.73%. Finally, the applicability and limitations of the newly proposed method were further discussed.https://doi.org/10.1038/s41598-024-77054-wPhotogrammetryJoint roughness coefficientJRC optimization3D reconstruction
spellingShingle Qinzheng Yang
Ang Li
Yipeng Liu
Hongtian Wang
Zhendong Leng
Fei Deng
Machine learning-based optimization of photogrammetric JRC accuracy
Scientific Reports
Photogrammetry
Joint roughness coefficient
JRC optimization
3D reconstruction
title Machine learning-based optimization of photogrammetric JRC accuracy
title_full Machine learning-based optimization of photogrammetric JRC accuracy
title_fullStr Machine learning-based optimization of photogrammetric JRC accuracy
title_full_unstemmed Machine learning-based optimization of photogrammetric JRC accuracy
title_short Machine learning-based optimization of photogrammetric JRC accuracy
title_sort machine learning based optimization of photogrammetric jrc accuracy
topic Photogrammetry
Joint roughness coefficient
JRC optimization
3D reconstruction
url https://doi.org/10.1038/s41598-024-77054-w
work_keys_str_mv AT qinzhengyang machinelearningbasedoptimizationofphotogrammetricjrcaccuracy
AT angli machinelearningbasedoptimizationofphotogrammetricjrcaccuracy
AT yipengliu machinelearningbasedoptimizationofphotogrammetricjrcaccuracy
AT hongtianwang machinelearningbasedoptimizationofphotogrammetricjrcaccuracy
AT zhendongleng machinelearningbasedoptimizationofphotogrammetricjrcaccuracy
AT feideng machinelearningbasedoptimizationofphotogrammetricjrcaccuracy