Image‐based road crack risk‐informed assessment using a convolutional neural network and an unmanned aerial vehicle

Abstract

Rapid crack assessment is widely thought to be critical for monitoring and maintaining roads in appropriate conditions. In this paper, a novel crackaffected risk-informed assessment framework is proposed for the monitoring and maintenance of roads. The framework includes five steps: data collection, crack detection, crack location extraction, crack real-size calculation, and risklevel assessment. To support the framework, an unmanned aerial vehicle (UAV) is used to monitor roads and collect data. A state-of-the-art semantic segmentation network, DeepLabv3+, is also applied to detect cracks. Based on the height and pixel statistics of the detected crack, the real size of the crack can be calculated using the pixel-physical conversion coefficient equation. This is followed by a risk-informed assessment of the road identifying the location of the crack for maintenance priority determination. Data collection and experiments using a UAV were performed on a real road to verify the feasibility and effectiveness of the proposed method. It was found that the proposed method was not only able to determine the real size of the cracks from the collected images but also able to determine their risk levels. In summary, this method presents a convenient and reliable solution for risk-informed road crack assessment that can be employed in practical applications.

Automatic pixel-level detection method for concrete crack with channel-spatial attention convolution neural network

“…to perform structural health monitoriing. 7 Ji et al 8 proposed a method of using the UAV to monitor road crack images, then use pixel statistics to detect cracks. In recent research, more scholars have paid attention to back-end image processing.…”

“…According to the application type, there are two main directions of technical diagnostics: monitoring and diagnostics of rotating machinery, [1][2][3][4] and structural health monitoring (SHM), which is defined as a process of implementing a damage detection and characterisation strategy for various engineering structures. [5][6][7][8] According to the used technique, diagnostic methods can be divided into: destructive technique when maximum load or fatigue test of samples are performed 9,10 ; and non-destructive technique when the state of the structure is evaluated without causing damage to it. 11,12 Due to this advantage, the nondestructive technique has become the most common technique for technical diagnostics nowadays.…”

“…Usually, for diagnostics are used: Visual diagnostics, Ultrasonic testing, Thermography; X-Ray testing, Eddy current; Electromagnetic Testing, Acoustic emission measurements, measurements and analysis of vibrations. 8,[13][14][15][16][17] Comparing all mentioned methods can be stated that vibration analysis is one of the most universal and commonly used methods of technical diagnostics since it is suitable for diagnostics of…”

A high‐frequency feature enhancement network for the surface defect detection of welded rebar

“…[18][19][20][21] With the introduction of a convolutional neural network (CNN), researchers found that this type of network based on convolution, pooling, and fully connected layers allows for automated feature extraction, and many automated damage detection methods are based on this type of network. [22][23][24] Zhang and Yuen 25 proposed a novel crack detection system; it is a fusion features-based broad learning system that has the advantage of efficient training without GPU acceleration. Kim et al 26 proposed a shallow CNN-based architecture for surface concrete crack detection, and the hyperparameters of the proposed model were optimized to achieve the maximum accuracy of crack detection with the least calculation.…”

“…To overcome these problems, researchers have proposed deep learning‐based methods 18–21 . With the introduction of a convolutional neural network (CNN), researchers found that this type of network based on convolution, pooling, and fully connected layers allows for automated feature extraction, and many automated damage detection methods are based on this type of network 22–24 . Zhang and Yuen 25 proposed a novel crack detection system; it is a fusion features‐based broad learning system that has the advantage of efficient training without GPU acceleration.…”