A Multi-Classifier System for Rock Mass Crack Segmentation Based on Convolutional Neural Networks

Asadi, Mohammadreza; Sadeghi, Mohammad Taghi; Bafghi, Alireza Yarahmadi

doi:10.1109/csicc52343.2021.9420613

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Byun et al [68] obtained a Jaccard index of 38% for extracting discontinuity lines with a CNN. Asadi et al [69] obtained an F1-score of 84%. Lee et al [25] obtained a Jaccard index of 62% for a similar purpose.…”

Section: Discussionmentioning

confidence: 97%

“…However, the model was overfit due to an insufficient amount of data. The proposed augmentation techniques are more suitable when compared to existing studies [25,27,28,68,69], and they have also resulted in significantly higher performance measures. Byun et al [68] obtained a Jaccard index of 38% for extracting discontinuity lines with a CNN.…”

Section: Discussionmentioning

confidence: 98%

See 1 more Smart Citation

A Novel Rock Mass Discontinuity Detection Approach with CNNs and Multi-View Image Augmentation

Yalcin,

Can,

Gokceoglu

et al. 2024

IJGI

View full text Add to dashboard Cite

Discontinuity is a key element used by geoscientists and civil engineers to characterize rock masses. The traditional approach to detecting and measuring rock discontinuity relies on fieldwork, which poses dangers to human life. Photogrammetric pattern recognition and 3D measurement techniques offer new possibilities without direct contact with rock masses. This study proposes a new approach to detect discontinuities using close-range photogrammetric techniques and convolutional neural networks (CNNs) trained on a small amount of data. Investigations were conducted on basalts in Bala, Ankara, Türkiye. A total of 34 multi-view images were collected with a remotely piloted aircraft system (RPAS), and discontinuity lines were manually delineated on a point cloud generated from these images. The lines were back-projected onto the raw images to increase the amount of data, a process we call multi-view (3D) augmentation. We further evaluated radiometric and geometric augmentation methods, the contribution of multi-view augmentation to the proposed model, and the transfer learning performance of six different CNN architectures. The highest performance was achieved with U-Net + SE-ResNeXt-50 with an F1-score of 90.6%. The CNN model trained from scratch with local features also yielded a similar F1-score (91.7%), which is the highest performance reported in the literature.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Discussionmentioning

confidence: 98%

A Novel Rock Mass Discontinuity Detection Approach with CNNs and Multi-View Image Augmentation

Yalcin,

Can,

Gokceoglu

et al. 2024

IJGI

View full text Add to dashboard Cite

show abstract

“…Imaged-based crack segmentation using deep learning has been widely applied for defect detection in man-made materials, such as asphalt and concrete [12], masonry wall [13], and steel [14]. Rock cores [15] and rock mass [16,17] have also been studied. These studies generally develop and compare the performance of models built using state-of-the-art CNN models such as DeepLabv3+ [18].…”

Section: Image-based Convolutionmentioning

confidence: 99%

“…Unlike the usual pixel-wise annotation practice, a simplified rock joint trace annotation strategy by using thin straight lines to reduce labelling time and computation cost is proposed [17]. Further, a weighted loss function that alleviates labelling uncertainty and class imbalance is proposed [23].…”

Section: Labelling Strategymentioning

confidence: 99%

See 1 more Smart Citation

Potential applications of deep learning in automatic rock joint trace mapping in a rock mass

Chiu

Mengshoel

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

In blasted rock slopes and underground openings, rock joints are visible in different forms. Rock joints are often exposed as planes confining rock blocks and visible as traces on a well-blasted, smooth rock mass surface. A realistic rock joint model should include both visual forms of joints in a rock mass: i.e., both joint traces and joint planes. Imaged-based 2D semantic segmentation using deep learning via the Convolutional Neural Network (CNN) has shown promising results in extracting joint traces in a rock mass. In 3D analysis, research studies using deep learning have demonstrated outperforming results in automatically extracting joint planes from an unstructured 3D point cloud compared to state-of-the-art methods. We discuss a pilot study using 3D true colour point cloud and their source and derived 2D images in this paper. In the study, we aim to implement and compare various CNN-based networks found in the literature for automatic extraction of joint traces from laser scanning and photogrammetry data. Extracted joint traces can then be clustered and connected to potential joint planes as joint objects in a discrete joint model. This can contribute to a more accurate estimation of rock joint persistence. The goal of the study is to compare the efficiency and accuracy between using 2D images and 3D point cloud as input data. Data are collected from two infrastructure projects with blasted rock slopes and tunnels in Norway.

show abstract

Asymmetric exponential loss function for crack segmentation

et al. 2022

View full text Add to dashboard Cite

A Multi-Classifier System for Rock Mass Crack Segmentation Based on Convolutional Neural Networks

Cited by 5 publications

References 17 publications

A Novel Rock Mass Discontinuity Detection Approach with CNNs and Multi-View Image Augmentation

A Novel Rock Mass Discontinuity Detection Approach with CNNs and Multi-View Image Augmentation

Potential applications of deep learning in automatic rock joint trace mapping in a rock mass

Asymmetric exponential loss function for crack segmentation

Contact Info

Product

Resources

About