Comparative detection of rock cracks based on two convolutional neural networks

Xuegang Zhang; Tao Wang; Shanji Chen; Yubo Wang

doi:10.1117/12.3049238

12 November 2024 Comparative detection of rock cracks based on two convolutional neural networks

Xuegang Zhang, Tao Wang, Shanji Chen, Yubo Wang

Author Affiliations +

Proceedings Volume 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) ; 133952Q (2024) https://doi.org/10.1117/12.3049238
Event: International Conference on Optics, Electronics, and Communication Engineering, 2024, Wuhan, China

Abstract

Rock mass fractures are one of the main factors leading to slope instability, and the detection of rock mass fractures can predict slope instability to a certain extent. The rapid development of deep learning has provided a low-cost and efficient method for the detection of rock mass fractures. This paper employs the DenseNet121 model and the InceptionV2 model for the detection of rock mass fractures, and improves the models by incorporating an attention mechanism. The dataset consists of rock masses with fractures from various regions to enhance the model’s applicability in different scenarios. Experiments have revealed that the InceptionV2 family of models exhibits overall better performance than the DenseNet121 family of models. Among them, the InceptionV2-ECA model performs the best with an F1 score of 0.9850 and an accuracy rate of 98.73%. Compared to the original InceptionV2 model, the accuracy rate has increased by 9.57%.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xuegang Zhang, Tao Wang, Shanji Chen, and Yubo Wang "Comparative detection of rock cracks based on two convolutional neural networks", Proc. SPIE 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) , 133952Q (12 November 2024); https://doi.org/10.1117/12.3049238

Access the abstract

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Performance modeling

Data modeling

Deep learning

Convolutional neural networks

Education and training

Engineering

Convolution

Show All Keywords

RELATED CONTENT

Drainage pipe defect identification based on convolutional neural network
Proceedings of SPIE (March 16 2023)

A pneumonia classification accuracy enhancement scheme based on data augmentation,...
Proceedings of SPIE (May 23 2023)

Graptolite image classification based on feature transfer and mixup data...
Proceedings of SPIE (August 01 2023)

Architectural style classification of the Chinese traditional settlements using deep...
Proceedings of SPIE (February 10 2023)

Transfer learning with deep models for small food datasets
Proceedings of SPIE (August 10 2023)

Domain adaptation strategy for aging and damage classification model of...
Proceedings of SPIE (October 11 2023)

Improved VGG network face expression recognition based on attention mechanism
Proceedings of SPIE (July 19 2024)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years