Article
Computer Science, Information Systems
Ahcene Arbaoui, Abdeldjalil Ouahabi, Sebastien Jacques, Madina Hamiane
Summary: This paper proposes a new methodology for crack detection and monitoring in concrete structures based on multiresolution analysis and deep learning, aiming to monitor crack propagation through automatic crack type identification. By combining wavelets and deep learning tools, it achieves a high accuracy close to 90%.
Article
Computer Science, Interdisciplinary Applications
Xiongyao Xie, Jielong Cai, Haozheng Wang, Qiang Wang, Jieying Xu, Yingxin Zhou, Biao Zhou
Summary: This study proposes a deep learning-based model called sparse-sensing and superpixel-based segmentation (SSSeg) for accurate and efficient crack segmentation. The SSSeg outperforms other models in accuracy and efficiency.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Remote Sensing
Marianna Christaki, Christos Vasilakos, Ermioni-Eirini Papadopoulou, Georgios Tataris, Ilias Siarkos, Nikolaos Soulakellis
Summary: This paper discusses methods for detecting changes in building stock during the recovery phase following an earthquake, using UAV images and artificial neural networks. The study shows that the combination of GLCM texture feature changes with ANN can accurately predict structural changes in buildings, achieving an accuracy of nearly 92%.
Article
Geochemistry & Geophysics
Wang Xia, Li Yan, Hong Xie
Summary: Traditional 2D textures cannot accurately represent the textures of objects in the 3D world, and existing 3D texture research can only handle volumetric data rather than geometric data. In this paper, we propose a co-occurrence matrix based on the digital surface model, which considers the spectral distribution on the 3D surface to represent the real textures of objects. Experimental results demonstrate that this method outperforms traditional textures in identifying different categories.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Materials Science, Multidisciplinary
Xiaoning Cui, Qicai Wang, Jinpeng Dai, Sheng Li, Chao Xie, Jianqiang Wang
Summary: Materials surface damage identification using computer vision technology is a research hotspot, with deep residual attention convolutional neural network (DRACNN) showing better classification performance for concrete cracks at pixel-level compared to other mainstream algorithms. The DRACNN achieves an IoU of 73.95%, accuracy of 97.82%, precision of 78.48%, and recall of 67.95%.
Article
Computer Science, Software Engineering
Anna Darzi, Itai Lang, Ashutosh Taklikar, Hadar Averbuch-Elor, Shai Avidan
Summary: As image generation techniques mature, there is a growing interest in developing explainable representations that are easy to understand and manipulate. In this work, the authors propose a fully convolutional generative adversarial network, conditioned locally on co-occurrence statistics, to generate large images with local, interpretable control over texture appearance. They introduce a novel differentiable co-occurrence loss to encourage fidelity to the input condition, and demonstrate a stable and intuitive latent representation for texture synthesis.
COMPUTATIONAL VISUAL MEDIA
(2022)
Article
Multidisciplinary Sciences
Shaswati Roy, Pradipta Maji
Summary: The paper presents a new method for assessing tumor grades using conventional MR sequences and the support vector machine classifier. Wavelet fusion technique based on texture information content is proposed to capture more informative features for characterizing tumor type. The proposed method achieves high classification performance on real brain MR data sets with six evaluation indices.
Article
Computer Science, Interdisciplinary Applications
Yang Liu, Mingxin Gao
Summary: A method based on the baseline model of the visual characteristics of images (BMVCI) is proposed to detect cracks in concrete structures. Compared with edge detection methods, BMVCI expands the quasi-distance between crack edges and image background, improving crack detection accuracy. Moreover, the method achieves higher computational efficiency and accuracy compared to deep learning methods.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Construction & Building Technology
Yangzhao Liu, Kaoshan Dai, Desheng Li, Mingyan Luo, Ye Liu, Yuanfeng Shi, Jun Xu, Zhenhua Huang
Summary: In this paper, a rapid damage assessment method of concrete components based on the fractal characteristics of concrete cracks was proposed. By establishing databases of crack FD versus loading-ratio, linear regressions were used to predict loading ratio for damage assessment. Experimental results showed that the proposed method is reliable for identifying potential damage levels in concrete components.
JOURNAL OF BUILDING ENGINEERING
(2021)
Article
Automation & Control Systems
Jia Xuan Li, Bo Zhou, Lun Li, Ji Bin Zhao, Guang Zhu, Ming Cai
Summary: This paper proposes a new method for analyzing the texture features of polished surfaces based on co-occurrence matrix, which accurately describes and analyzes the texture features. This method can be used in the path planning stage, avoiding resource waste and being unaffected by image quality.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Forestry
Jyrki Savolainen
Summary: This paper proposes a method for tracking wooden veneer sheets by matching their wet and dry colour images. The method involves image segmentation, extraction of GLCM textural feature arrays, and similarity comparisons. A voting mechanism is introduced for determining the correct match, and an optional shifting procedure is applied for candidates with missing areas. The proposed method achieves a matching accuracy of 99.41% on a real-world dataset, outperforming previous studies and offering practical implications for automated veneer production facilities.
EUROPEAN JOURNAL OF WOOD AND WOOD PRODUCTS
(2023)
Article
Construction & Building Technology
Yonggang Shen, Zhenwei Yu, Chunsheng Li, Chao Zhao, Zhilin Sun
Summary: This paper proposes an improved algorithm based on the open-source model Deeplabv3+ for concrete crack detection. By using a lightweight network model and a new training strategy, the algorithm achieves accurate and real-time detection of concrete cracks.
Article
Computer Science, Interdisciplinary Applications
Hao Chen, Wei Li, Youyu Zhu
Summary: This study aimed to differentiate benign from malignant pulmonary nodules based on the improved GLCM algorithm and texture analysis technique. Various parameters and analysis methods were used, and the combination of NDA and FPM significantly reduced the MCR value, providing valuable reference for the early diagnosis of lung cancer.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Mechanics
Lixia Pan, Julian Carrillo, Maosen Cao, Ganggang Sha
Summary: This study introduces the use of multifractal analysis (MUTFA) to characterize the distribution and evolution of cracks in reinforced concrete (RC) structures, and proposes a new multifractal-spectrum shape parameter. The results demonstrate that this method can effectively reveal the complexity and irregularity of crack distributions, which helps in assessing damage in concrete structures.
ENGINEERING FRACTURE MECHANICS
(2022)
Article
Engineering, Multidisciplinary
Sarah Miele, Pranav M. Karve, Sankaran Mahadevan, Vivek Agarwal
Summary: This paper investigates the utility of physics-informed machine learning models for vibro-acoustic modulation (VAM)-based damage localization in concrete structures. The proposed methodology automates the threshold selection, increases the speed of the probabilistic damage diagnosis process, and enables the estimation of damage depth. The proposed physics-informed machine learning models for VAM-based damage diagnosis achieve an accuracy of about 60-64% in the validation experiments, indicating their potential for internal crack detection.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Engineering, Geological
Ali Fathi, Zabihallah Moradian, Patrice Rivard, Gerard Ballivy, Andrew J. Boyd
ROCK MECHANICS AND ROCK ENGINEERING
(2016)
Article
Engineering, Geological
D. Sow, P. Rivard, L. Peyras, P. Breul, Z. A. Moradian, C. Bacconnet, G. Ballivy
ROCK MECHANICS AND ROCK ENGINEERING
(2016)
Article
Engineering, Geological
Djibril Sow, Claudio Carvajal, Pierre Breul, Laurent Peyras, Patrice Rivard, Claude Bacconnet, Gerard Ballivy
ENGINEERING GEOLOGY
(2017)
Article
Engineering, Geological
Arash Khosravi, Richard Simon, Patrice Rivard
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2017)
Article
Engineering, Geological
O. Nouailletas, C. Perlot, P. Rivard, G. Ballivy, C. La Borderie
ROCK MECHANICS AND ROCK ENGINEERING
(2017)
Article
Construction & Building Technology
Bassili Guirguis, Medhat H. Shehata, Josee Duchesne, Benoit Fournier, Benoit Durand, Patrice Rivard
CONSTRUCTION AND BUILDING MATERIALS
(2018)
Article
Engineering, Chemical
Amine el Mandi Safhi, Mahfoud Benzerzour, Patrice Rivard, Nor-Edine Abriak
Article
Construction & Building Technology
Yasaman Khajehnouri, Michel Chouteau, Patrice Rivard, Charles L. Berube
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Engineering, Geological
Adrien Rulliere, Patrice Rivard, Laurent Peyras, Pierre Breul
JOURNAL OF GEOTECHNICAL AND GEOENVIRONMENTAL ENGINEERING
(2020)
Article
Construction & Building Technology
Abdelhadi Bouchikhi, Amine el Mahdi Safhi, Patrice Rivard, Ruben Snellings, Nor-Edine Abriak
Summary: This paper assesses the recycling of thermally treated fluvial sediments as supplementary cementitious materials. Different calcination treatments were conducted, and the resulting blended cements were tested, showing that blended cement based on 750 degrees C calcined sediments had the best hydration kinetics and compressive strength. An optimization design of experiment suggests the maximum substitution rate for producing blended cement equivalent to different cement types.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2022)
Article
Engineering, Mechanical
E. M. B. Medfouni, A. S. Kodjo, P. Rivard
Summary: Pins installed in rock mass serve to prevent falling rocks and debris that may pose a danger to infrastructure and workers. Laboratory tests were conducted to assess the performance of the galvanized protective layer of the pins under various aggressive conditions. Results showed that the zinc layer offers the highest level of protection, even when damaged, but leaching rates from sand can affect the effectiveness of galvanization.
EXPERIMENTAL TECHNIQUES
(2023)
Article
Construction & Building Technology
Yassine Abriak, Walid Maherzi, Mahfoud Benzerzour, Ahmed Senouci, Patrice Rivard
Summary: Large quantities of dredged sediments and recycled concrete materials are being generated annually worldwide, causing environmental problems when disposed of in landfills. Depletion of high-quality construction raw materials necessitates finding alternative options. This study investigates the potential of using dredged sediments and recycled concrete aggregates in road subgrade construction, and the test results confirm their feasibility in meeting the required physical, mechanical, and geotechnical properties. Additionally, leaching tests demonstrate the environmental safety of the proposed mixes for road subgrade construction, with future studies exploring their usage in foundations and base layers.
Proceedings Paper
Construction & Building Technology
Amine El Mahdi Safhi, Patrice Rivard, Mahfoud Benzerzour, Nor-Edine Abriak
Summary: The consumption of natural materials for construction purpose is increasing each year while the resources are limited. To reduce the environmental burden and efficiently optimize resources, the use of local and alternative resources as building materials is necessary. This study explores the feasibility of using consolidated sandy sediments as artificial rock for coastal protection against erosion in the Magdalen Islands of Quebec.
PROCEEDINGS OF THE 75TH RILEM ANNUAL WEEK 2021
(2023)
Article
Construction & Building Technology
Yassine Abriak, Duc Chinh Chu, Walid Maherzi, Mahfoud Benzerzour, Patrice Rivard
Summary: This study investigates the influence of fine powder obtained from recycled concrete aggregate on the hydration kinetics and mechanical-microstructural properties of hydrated cement. Experimental results show that the presence of calcite and residual hydrates in the fine powder accelerates the hydration of cement phases. Increasing the substitution level of the fine powder also increases the degree of hydration of cement, although it may slightly delay hydration at very early ages.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Engineering, Environmental
Hamza Kebab, Abederrahmane Boumezbeur, Patrice Rivard
Summary: Dams are designed to withstand severe conditions, with most failures attributed to foundation problems, particularly related to discontinuities in rock foundations. This study focused on the suitability of the Ypresian limestone rock mass as a foundation for the Beni Haroun dam in Algeria, showing that it is suitable for this purpose.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
