Summary of Pavement Fatigue Crack Detection and Severity Classification Based on Convolutional Neural Network, by Zhen Wang and Dylan G. Ildefonzo and Linbing Wang
Pavement Fatigue Crack Detection and Severity Classification Based on Convolutional Neural Network
by Zhen Wang, Dylan G. Ildefonzo, Linbing Wang
First submitted to arxiv on: 22 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel deep convolutional neural network that can classify fatigue cracking in asphalt pavements based on surface images. The network achieves two objectives: classifying the presence and severity level of fatigue cracking using the Distress Identification Manual (DIM) standard. The researchers establish a databank of 4,484 high-resolution pavement surface images taken in Blacksburg, Virginia, USA, and manually label over 4,000 images into four categories based on DIM standards. A four-layer convolutional neural network model is built to classify images by pavement crack severity category. The trained model achieves a crack existence classification accuracy of 96.23% and a severity level classification accuracy of 96.74%, outperforming existing methods. Additionally, the model can accurately detect pavement markings with an accuracy of 97.64%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to better detect cracks in asphalt roads using computer vision technology. The researchers created a special tool that can look at pictures of road surfaces and tell if there are any cracks present, and also how bad the cracking is. They used lots of images taken from real roads in Virginia to train this tool, and it was able to correctly identify cracks most of the time. This could help us keep our roads safer and more reliable. |
Keywords
» Artificial intelligence » Classification » Neural network
