Detection of road cracks using Convolutional Neural Networks and Threshold Segmentation
Automatic road crack detection is a vital transportation maintenance responsibility for ensuring driving comfort and safety. However, manual inspection is considered risky because it is time-consuming, costly, and dangerous for inspectors. Automated road crack detecting techniques have been extensiv...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Asosiasi Staf Akademik Perguruan Tinggi Seluruh Indonesia (ASASI)
2022
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/102443/1/102443_Detection%20of%20road%20cracks%20using%20Convolutional%20Neural%20Networks%20and%20Threshold%20Segmentation.pdf http://irep.iium.edu.my/102443/ http://asasijournal.id/index.php/jiae/article/view/82 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Automatic road crack detection is a vital transportation maintenance responsibility for ensuring driving comfort and safety. However, manual inspection is considered risky because it is time-consuming, costly, and dangerous for inspectors. Automated road crack detecting techniques have been extensively researched and developed in order to overcome this issue. Despite the difficulties, most proposed methodologies and solutions involve machine vision and machine learning, which have recently acquired traction largely due to the increasingly more affordable processing power. Nonetheless, it remains a difficult task due to the inhomogeneity of crack intensity and the intricacy of the background. In this paper, a convolutional neural network-based method for crack detection is proposed. Recent advancements inspire the method of machine learning to computer vision. The primary goal of this work is to employ convolutional neural networks to detect road cracks. Data in the form of images has been used as input, preprocessing, and threshold segmentation are applied to the input data. The processed output is fed to CNN for feature extraction and classification. The training accuracy was found to be 96.20 %, the validation accuracy to be 96.50 %, and the testing accuracy to be 94.5 %. |
---|