Related Concept Videos
Microcracking in Concrete
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.
Design Example: Joints in Concrete Pavements
Contraction joints are typically formed by sawing a groove into the concrete shortly after it has hardened. This creates a weakened vertical plane, deliberately encouraging cracking at...
Abrasion Resistance of Concrete
One such test is the revolving disc test, where three plates...
Creep in Concrete
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Residual metric learning with class-specific consistency for multiclass classification.
Survivin, the promising target in hepatocellular carcinoma gene therapy.
Curcumin protects dopaminergic neuron against LPS induced neurotoxicity in primary rat neuron/glia culture.
Related Experiment Video
Updated: May 29, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
Image recognition technology for bituminous concrete reservoir panel cracks based on deep learning.
Kai Hu1,2, Yang Ling2, Jie Liu3
1School of Civil Engineering and Architecture, Xi'an Technological University, Xi 'an, Shaanxi, China.
This study presents an advanced deep learning anomaly model for detecting asphalt concrete cracks. The novel approach significantly improves accuracy and robustness, even under challenging environmental conditions.
More Related Videos
00:05Crack Monitoring in Resonance Fatigue Testing of Welded Specimens Using Digital Image Correlation
Published on: September 29, 2019
12:18Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography
Published on: October 21, 2018
Area of Science:
- Civil Engineering
- Computer Science
- Artificial Intelligence
Background:
- Crack detection in asphalt concrete is hindered by environmental factors affecting image quality and accuracy.
- Existing methods struggle with variations in lighting, reflections, and weather.
Purpose of the Study:
- To introduce a novel deep learning-based anomaly model for accurate and robust crack detection in asphalt concrete.
- To enhance feature extraction, weighting, and information transmission for improved detection performance.
Main Methods:
- Collected and processed a large dataset of panel images using denoising, standardization, and data augmentation.
- Developed an improved Xception network incorporating an adaptive activation function, dynamic attention mechanism, and multi-level residual connections.
- Utilized LabelImg software for precise labeling of crack areas.
Main Results:
- The enhanced deep learning model achieved 97.6% accuracy and a Matthews correlation coefficient of 0.98.
- Demonstrated stable performance and high accuracy under varying lighting conditions.
- Significantly improved feature extraction, weighting, and information transmission capabilities.
Conclusions:
- The novel deep learning anomaly model offers a significant advancement in asphalt concrete crack detection.
- The proposed method enhances detection accuracy, robustness, and efficiency, overcoming environmental challenges.
- This approach provides a valuable tool for infrastructure monitoring and maintenance.