Developing a new deep learning CNN model to detect and classify highway cracks

Elghaish, F, Talebi, S, Abdellatef, E, Matarneh, ST, Hosseini, MR, Wu, S ORCID: https://orcid.org/0000-0002-5633-2229, Mayouf, M, Hajirasouli, A and Nguyen, T-Q, 2021. Developing a new deep learning CNN model to detect and classify highway cracks. Journal of Engineering, Design and Technology. ISSN 1726-0531

Preview

Text 1512279_Wu.pdf - Post-print Download (1MB) | Preview

Abstract

Purpose: This paper aims to Test the capabilities/accuracies of four deep learning pre trained convolutional neural network (CNN) models to detect and classify types of highway cracks, as well as developing a new CNN model to maximize the accuracy at different learning rates.

Design/methodology/approach: A sample of 4,663 images of highway cracks were collected and classified into three categories of cracks, namely, "vertical cracks," "horizontal and vertical cracks" and "diagonal cracks," subsequently, using "Matlab" to classify the sample to training (70%) and testing (30%) to apply the four deep learning CNN models and compute their accuracies. After that, developing a new deep learning CNN model to maximize the accuracy of detecting and classifying highway cracks and testing the accuracy using three optimization algorithms at different learning rates.

Findings: The accuracies result of the four deep learning pre-trained models are above the averages between top-1 and top-5 and the accuracy of classifying and detecting the samples exceeded the top-5 accuracy for the pre-trained AlexNet model around 3% and by 0.2% for the GoogleNet model. The accurate model here is the GoogleNet model as the accuracy is 89.08% and it is higher than AlexNet by 1.26%. While the computed accuracy for the new created deep learning CNN model exceeded all pre-trained models by achieving 97.62% at a learning rate of 0.001 using Adam’s optimization algorithm.

Practical implications: The created deep learning CNN model will enable users (e.g. highway agencies) to scan a long highway and detect types of cracks accurately in a very short time compared to traditional approaches.

Originality/value: A new deep learning CNN-based highway cracks detection was developed based on testing four pre-trained CNN models and analyze the capabilities of each model to maximize the accuracy of the proposed CNN.

Item Type:	Journal article
Publication Title:	Journal of Engineering, Design and Technology
Creators:	Elghaish, F., Talebi, S., Abdellatef, E., Matarneh, S.T., Hosseini, M.R., Wu, S., Mayouf, M., Hajirasouli, A. and Nguyen, T.-Q.
Publisher:	Emerald
Date:	16 August 2021
ISSN:	1726-0531
Identifiers:	Number Type 10.1108/jedt-04-2021-0192 DOI 1512279 Other
Divisions:	Schools > School of Architecture, Design and the Built Environment
Record created by:	Linda Sullivan
Date Added:	31 Jan 2022 11:15
Last Modified:	31 Jan 2022 11:15
URI:	https://irep.ntu.ac.uk/id/eprint/45455

Actions (login required)

Edit View

Statistics

Views

Downloads