Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features
To enhance the accuracy of joint roughness coefficient (JRC) estimation in photogrammetry, this study employed a fixed-camera shooting strategy guided by a Structure-from-Motion-based shooting parameter selection algorithm to reconstruct 3D models of rock samples at 16 different shooting distances....
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2025.1497871/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582902393602048 |
|---|---|
| author | Jiang Yuan Qing Wang Qinzheng Yang Yongqiang Fan Weining Jiao |
| author_facet | Jiang Yuan Qing Wang Qinzheng Yang Yongqiang Fan Weining Jiao |
| author_sort | Jiang Yuan |
| collection | DOAJ |
| description | To enhance the accuracy of joint roughness coefficient (JRC) estimation in photogrammetry, this study employed a fixed-camera shooting strategy guided by a Structure-from-Motion-based shooting parameter selection algorithm to reconstruct 3D models of rock samples at 16 different shooting distances. The analysis at profile intervals of 0.25 mm, 0.5 mm, and 1 mm revealed a strong correlation between JRC accuracy and three parameters: object space resolution error, spatial distance between point cloud points, and spatial errors of checkpoints on the orientation board. Using these three parameters as input variables and JRC error as the output variable, five machine learning algorithms—Support Vector Regression, Gaussian Process Regression, Multilayer Perceptron, XGBoost, and CatBoost—were employed to predict JRC errors across different shooting distances. The Multilayer Perceptron model performed best at profile intervals of 0.25 mm and 0.5 mm, while XGBoost was optimal at the 1 mm interval. Under the predictions of these models, JRC accuracy improved by an average of 84.7% across the three intervals. Finally, the applicability and limitations of the proposed method were further discussed. |
| format | Article |
| id | doaj-art-6023593fade24005a825383fe52c7062 |
| institution | Kabale University |
| issn | 2296-6463 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj-art-6023593fade24005a825383fe52c70622025-01-29T06:46:03ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-01-011310.3389/feart.2025.14978711497871Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud featuresJiang Yuan0Qing Wang1Qinzheng Yang2Yongqiang Fan3Weining Jiao4CCCC Second Highway Engineering Co., Ltd., Xi’an, ChinaCCCC Second Highway Engineering Co., Ltd., Xi’an, ChinaSchool of Highway, Chang’an University, Xi’an, ChinaCCCC Second Highway Engineering Co., Ltd., Xi’an, ChinaCCCC Second Highway Engineering Co., Ltd., Xi’an, ChinaTo enhance the accuracy of joint roughness coefficient (JRC) estimation in photogrammetry, this study employed a fixed-camera shooting strategy guided by a Structure-from-Motion-based shooting parameter selection algorithm to reconstruct 3D models of rock samples at 16 different shooting distances. The analysis at profile intervals of 0.25 mm, 0.5 mm, and 1 mm revealed a strong correlation between JRC accuracy and three parameters: object space resolution error, spatial distance between point cloud points, and spatial errors of checkpoints on the orientation board. Using these three parameters as input variables and JRC error as the output variable, five machine learning algorithms—Support Vector Regression, Gaussian Process Regression, Multilayer Perceptron, XGBoost, and CatBoost—were employed to predict JRC errors across different shooting distances. The Multilayer Perceptron model performed best at profile intervals of 0.25 mm and 0.5 mm, while XGBoost was optimal at the 1 mm interval. Under the predictions of these models, JRC accuracy improved by an average of 84.7% across the three intervals. Finally, the applicability and limitations of the proposed method were further discussed.https://www.frontiersin.org/articles/10.3389/feart.2025.1497871/fullphotogrammetryrock surface roughnessJRC optimization3D reconstrutionmachine learning |
| spellingShingle | Jiang Yuan Qing Wang Qinzheng Yang Yongqiang Fan Weining Jiao Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features Frontiers in Earth Science photogrammetry rock surface roughness JRC optimization 3D reconstrution machine learning |
| title | Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features |
| title_full | Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features |
| title_fullStr | Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features |
| title_full_unstemmed | Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features |
| title_short | Improvement of rock surface roughness accuracy by combining object space resolution error and 3D point cloud features |
| title_sort | improvement of rock surface roughness accuracy by combining object space resolution error and 3d point cloud features |
| topic | photogrammetry rock surface roughness JRC optimization 3D reconstrution machine learning |
| url | https://www.frontiersin.org/articles/10.3389/feart.2025.1497871/full |
| work_keys_str_mv | AT jiangyuan improvementofrocksurfaceroughnessaccuracybycombiningobjectspaceresolutionerrorand3dpointcloudfeatures AT qingwang improvementofrocksurfaceroughnessaccuracybycombiningobjectspaceresolutionerrorand3dpointcloudfeatures AT qinzhengyang improvementofrocksurfaceroughnessaccuracybycombiningobjectspaceresolutionerrorand3dpointcloudfeatures AT yongqiangfan improvementofrocksurfaceroughnessaccuracybycombiningobjectspaceresolutionerrorand3dpointcloudfeatures AT weiningjiao improvementofrocksurfaceroughnessaccuracybycombiningobjectspaceresolutionerrorand3dpointcloudfeatures |