Related Concept Videos
Segregation in Fresh Concrete
Placing Concrete
While placing concrete, care is taken to ensure that the concrete is laid in uniform layers, and hand shoveling and moving concrete using poker vibrators is avoided. Also,...
Bleeding in Fresh Concrete
Bleeding can cause several issues in the concrete structure. Sometimes, the rising water gets trapped beneath large aggregate...
Non-destructive Tests for Concrete Strength
Types of Non-structural Cracks in Concrete
Plastic shrinkage cracks typically form within hours after the concrete is poured. The concrete's surface dries faster than the bottom, creating tensile stress that the still-plastic concrete cannot withstand, leading to diagonal or randomly patterned cracks on the concrete surface.
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Incorporation of Nitinol (NiTi) Shape Memory Alloy (SMA) in Concrete: A Review.
Effects of low cycle fatigue and inelastic buckling on the superelasticity and energy dissipation capacity of NiTi SMA rebar.
Mechanical properties and constitutive models of shape memory alloy for structural engineering: A review.
Performance Comparison of Multiple Convolutional Neural Networks for Concrete Defects Classification.
Learning monocular depth estimation for defect measurement from civil RGB-D dataset.
Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar.
Deep learning-based obstacle-avoiding autonomous UAVs with fiducial marker-based localization for structural health monitoring.
Efficient attention-based deep encoder and decoder for automatic crack segmentation.
Related Experiment Video
Updated: Jul 8, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
Deep learning-based concrete defects classification and detection using semantic segmentation.
Palisa Arafin1, Ahm Muntasir Billah2, Anas Issa3
1Department of Civil Engineering, Lakehead University, Thunder Bay, ON, Canada.
This study introduces a new dataset and deep learning models for concrete crack and spalling detection in structural health monitoring. EfficientNetB3-based U-Net achieved 95.66% F1-score for crack segmentation.
More Related Videos
Area of Science:
- Civil Engineering
- Computer Science
- Artificial Intelligence
Background:
- Deep learning (DL) offers potential for accurate, objective infrastructure damage detection in structural health monitoring (SHM).
- Key challenges include limited defect image datasets and selecting appropriate DL network architectures for real-time applications.
Purpose of the Study:
- To develop and evaluate DL models for concrete crack and spalling detection using a novel dataset.
- To address limitations in existing defect image databases and DL network depth selection for SHM.
Main Methods:
- A diverse dataset of 4087 concrete crack and 1100 spalling images was created.
- Convolutional Neural Network (CNN) classifiers (VGG19, ResNet50, InceptionV3) were used for defect identification.
- Encoder-decoder models (U-Net, PSPNet) with various backbones (VGG19, ResNet50, InceptionV3, EfficientNetB3) were developed for semantic segmentation.
Main Results:
- InceptionV3 achieved 91.98% accuracy for defect classification with the RMSprop optimizer.
- EfficientNetB3-based U-Net yielded the best crack segmentation (95.66% F1-score).
- InceptionV3-based U-Net excelled in spalling segmentation (89.43% F1-score).
Conclusions:
- The developed DL models and dataset significantly advance automated visual damage detection in SHM.
- Specific CNN architectures demonstrate high efficacy for both classification and segmentation of concrete defects.
- This research provides a foundation for more accurate and accessible real-time structural health monitoring systems.

