CVAILGApr 6, 2023

Convolutional neural networks for crack detection on flexible road pavements

arXiv:2304.02933v12 citationsh-index: 15
Originality Synthesis-oriented
AI Analysis

This work addresses the tedious manual process of road crack surveying, offering an automated solution to reduce human bias and error, though it is incremental as it applies existing methods to a new dataset.

The study compared six convolutional neural network models for detecting cracks on flexible road pavements, achieving up to 98% accuracy on a new dataset of 14,000 samples.

Flexible road pavements deteriorate primarily due to traffic and adverse environmental conditions. Cracking is the most common deterioration mechanism; the surveying thereof is typically conducted manually using internationally defined classification standards. In South Africa, the use of high-definition video images has been introduced, which allows for safer road surveying. However, surveying is still a tedious manual process. Automation of the detection of defects such as cracks would allow for faster analysis of road networks and potentially reduce human bias and error. This study performs a comparison of six state-of-the-art convolutional neural network models for the purpose of crack detection. The models are pretrained on the ImageNet dataset, and fine-tuned using a new real-world binary crack dataset consisting of 14000 samples. The effects of dataset augmentation are also investigated. Of the six models trained, five achieved accuracy above 97%. The highest recorded accuracy was 98%, achieved by the ResNet and VGG16 models. The dataset is available at the following URL: https://zenodo.org/record/7795975

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes