Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall

Traditional methods for panoramic unfolded image stitching of rock mass borehole walls suffer from insufficient robustness in establishing feature correspondences between adjacent images, as well as poor quality, limited quantity of extracted image feature points and otherc problems. Meanwhile, supe...

Full description

Saved in:
Bibliographic Details
Main Authors: XIAO Yu, LI Zehao, WANG Chao
Format: Article
Language:zho
Published: Editorial Department of Industry and Mine Automation 2025-05-01
Series:Gong-kuang zidonghua
Subjects:
Online Access:http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850085325974536192
author XIAO Yu
LI Zehao
WANG Chao
author_facet XIAO Yu
LI Zehao
WANG Chao
author_sort XIAO Yu
collection DOAJ
description Traditional methods for panoramic unfolded image stitching of rock mass borehole walls suffer from insufficient robustness in establishing feature correspondences between adjacent images, as well as poor quality, limited quantity of extracted image feature points and otherc problems. Meanwhile, supervised learning methods cannot obtain sufficiently precise labeled matching point pairs. To address these issues, an unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall is proposed. Multi-scale feature extraction was performed on two adjacent panoramic unfolded images of the rock mass borehole wall to be stitched, using a ResNet network improved with grouped convolutions. A matching degree cross-correlation calculation module was introduced to identify and align features within the feature maps, thereby determining the spatial relationships between corresponding feature maps. A global and local deformation offset calculation network module precisely aligned spatial features of the images. Furthermore, homography deformation and image grid deformation modules effectively eliminated feature distortions between adjacent images, achieving overall alignment and fine local adjustments, enabling accurate registration of local features and deformations. Experimental results showed that this method effectively overcame issues such as image feature displacement, content misalignment, loss of detailed features, and stitching failure. The stitching seams exhibited almost no visible artifacts, improving the overall quality and visual effect of the stitched images. The method outperforms other mainstream image stitching approaches in terms of Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR) in overlapping regions, and Structural Similarity (SSIM) index, significantly enhancing the stitching accuracy of panoramic unfolded images of rock mass borehole walls.
format Article
id doaj-art-6cbd6ed5cc414c4bbd624a863cb6bedb
institution DOAJ
issn 1671-251X
language zho
publishDate 2025-05-01
publisher Editorial Department of Industry and Mine Automation
record_format Article
series Gong-kuang zidonghua
spelling doaj-art-6cbd6ed5cc414c4bbd624a863cb6bedb2025-08-20T02:43:45ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2025-05-01515808610.13272/j.issn.1671-251x.2024100008Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wallXIAO Yu0LI Zehao1WANG Chao2School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaTraditional methods for panoramic unfolded image stitching of rock mass borehole walls suffer from insufficient robustness in establishing feature correspondences between adjacent images, as well as poor quality, limited quantity of extracted image feature points and otherc problems. Meanwhile, supervised learning methods cannot obtain sufficiently precise labeled matching point pairs. To address these issues, an unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall is proposed. Multi-scale feature extraction was performed on two adjacent panoramic unfolded images of the rock mass borehole wall to be stitched, using a ResNet network improved with grouped convolutions. A matching degree cross-correlation calculation module was introduced to identify and align features within the feature maps, thereby determining the spatial relationships between corresponding feature maps. A global and local deformation offset calculation network module precisely aligned spatial features of the images. Furthermore, homography deformation and image grid deformation modules effectively eliminated feature distortions between adjacent images, achieving overall alignment and fine local adjustments, enabling accurate registration of local features and deformations. Experimental results showed that this method effectively overcame issues such as image feature displacement, content misalignment, loss of detailed features, and stitching failure. The stitching seams exhibited almost no visible artifacts, improving the overall quality and visual effect of the stitched images. The method outperforms other mainstream image stitching approaches in terms of Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR) in overlapping regions, and Structural Similarity (SSIM) index, significantly enhancing the stitching accuracy of panoramic unfolded images of rock mass borehole walls.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100008panoramic unfolded images of rock mass borehole wallsimage stitchingunsupervised learningglobal and local deformation offsetshomography deformation
spellingShingle XIAO Yu
LI Zehao
WANG Chao
Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
Gong-kuang zidonghua
panoramic unfolded images of rock mass borehole walls
image stitching
unsupervised learning
global and local deformation offsets
homography deformation
title Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
title_full Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
title_fullStr Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
title_full_unstemmed Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
title_short Unsupervised learning-based panoramic unfolded image stitching method for rock mass borehole wall
title_sort unsupervised learning based panoramic unfolded image stitching method for rock mass borehole wall
topic panoramic unfolded images of rock mass borehole walls
image stitching
unsupervised learning
global and local deformation offsets
homography deformation
url http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2024100008
work_keys_str_mv AT xiaoyu unsupervisedlearningbasedpanoramicunfoldedimagestitchingmethodforrockmassboreholewall
AT lizehao unsupervisedlearningbasedpanoramicunfoldedimagestitchingmethodforrockmassboreholewall
AT wangchao unsupervisedlearningbasedpanoramicunfoldedimagestitchingmethodforrockmassboreholewall