The UAV-PDD2023 dataset consists of pavement distress images captured by unmanned aerial vehicles (UAVs) in China with more than 11,150 instances under two different weather conditions and across varying levels of construction quality. The roads in the dataset consist of highways, provincial roads, and county roads constructed under different requirements. It contains six typical types of pavement distress instances, including longitudinal cracks, transverse cracks, oblique cracks, alligator cracks, patching, and potholes. The dataset can be used to train deep learning models for automatically detecting and classifying pavement distresses using UAV images. In addition, the dataset can be used as a benchmark to evaluate the performance of different algorithms for solving tasks such as object detection, image classification, etc. The UAV-PDD2023 dataset can be downloaded for free at the URL in this paper.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10630617 | PMC |
| http://dx.doi.org/10.1016/j.dib.2023.109692 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
PaveDistress: A comprehensive dataset of pavement distresses detection.
Data Brief
December 2024
Department of Civil and Environmental Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ 08854, USA.
Article Synopsis
- The PaveDistress dataset consists of high-resolution images of various road surface distresses like cracks and potholes, all captured on the S315 highway in China using a specialized vehicle equipped with advanced imaging technology.
- The images, taken at 1mm intervals under diverse lighting conditions, are categorized into specific types of distresses, allowing for precise identification and measurement of defects.
- This dataset serves as a resource for developing deep learning models aimed at non-destructive road defect detection, benefiting civil engineering research and road maintenance systems.
Evaluating the dynamic response and phase angle behavior of SBS-modified asphalt mixtures for enhanced pavement performance.
Sci Rep
November 2024
College of Engineering, Prince Sultan University, Riyadh, 11586, Saudi Arabia.
Bitumen exhibits viscoelastic properties, showcasing both viscous and elastic behaviors, which are characterized by the phase angle and dynamic modulus. Issues like early fatigue fractures, rutting, and permanent deformations in bituminous asphalt pavements arise due to moisture susceptibility, high-temperature deformation, low-temperature cracking, and overloading. These distresses result in potholes, alligator cracks, and specific deformations that lead to early pavement failure, increasing rehabilitation and maintenance costs.
View Article and Find Full Text PDFLeveraging a deep learning generative model to enhance recognition of minor asphalt defects.
Sci Rep
November 2024
GITECO Research Group, University of Cantabria, 39005, Santander, Spain.
Deep learning-based computer vision systems have become powerful tools for automated and cost-effective pavement distress detection, essential for efficient road maintenance. Current methods focus primarily on developing supervised learning architectures, which are limited by the scarcity of annotated image datasets. The use of data augmentation with synthetic images created by generative models to improve these supervised systems is not widely explored.
View Article and Find Full Text PDFRoad Defect Identification and Location Method Based on an Improved ML-YOLO Algorithm.
Sensors (Basel)
October 2024
School of Geosciences, Yangtze University, Wuhan 430074, China.
The conventional method for detecting road defects relies heavily on manual inspections, which are often inefficient and struggle with precise defect localization. This paper introduces a novel approach for identifying and locating road defects based on an enhanced ML-YOLO algorithm. By refining the YOLOv8 object detection framework, we optimize both the traditional convolutional layers and the spatial pyramid pooling network.
View Article and Find Full Text PDFResearch on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning.
Sci Rep
October 2024
School of Civil Engineering, Hunan City University, Yiyang, 413000, China.
Accurate detection of asphalt pavement distress is crucial for road maintenance and traffic safety. However, traditional convolutional neural networks usually struggle with this task due to the varied distress patterns and complex background in the images. To enhance the accuracy of asphalt pavement distress identification across various scenarios, this paper introduces an improved model named SMG-YOLOv8, based on the YOLOv8s framework.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!