Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 11 (2022)  /  Artículo
ARTÍCULO
TITULO

Pavement Distress Detection Using Three-Dimension Ground Penetrating Radar and Deep Learning

Jiangang Yang    
Kaiguo Ruan    
Jie Gao    
Shenggang Yang and Lichao Zhang    

Resumen

Three-dimensional ground penetrating radar (3D GPR) is a non-destructive examination technology for pavement distress detection, for which its horizontal plane images provide a unique perspective for the task. However, a 3D GPR collects thousands of horizontal plane images per kilometer of the investigated pavement. The existing detection methods using GPR images are time-consuming and risky for subjective judgment. To solve the problem, this study used deep learning methods and 3D GPR horizontal plane images to detect pavement structural distress, including cracks, repairs, voids, poor interlayer bonding, and mixture segregation. In this study, two deep learning methods, called CP-YOLOX and SViT, were used to achieve the aim. A dataset for anomalous waveform localization (3688 images) was first created by pre-processing 3D-GPR horizontal plane images. A CP-YOLOX model was then trained to localize anomalous waveforms. Five SViT models with different numbers of encoders were adopted to perform the classification of anomalous waveforms using the localization results from the CP-YOLOX model. The numerical experiment results showed that 3D GPR horizontal plane images have the potential to be an assistant for pavement structural distress detection. The CP-YOLOX model achieved 87.71% precision, 80.64% mAP, and 33.57 sheets/s detection speed in locating anomalous waveforms. The optimal SViT achieved 63.63%, 68.12%, and 75.57% classification accuracies for the 5-category, 4-category, and 3-category datasets, respectively. The proposed models outperformed other deep learning methods on distress detection using 3D GPR horizontal plane images. In the future, more radar images should be collected to improve the accuracy of SViT.

 Artículos similares

       
 
Abdualmtalab Ali, Usama Heneash, Amgad Hussein and Mohamed Eskebi    
The fuzzy logic technique is one of the effective approaches for evaluating flexible and rigid pavement distress. The process of classifying pavement distress is usually performed by visual inspection of the pavement surface or using data collected by au... ver más
Revista: Infrastructures

 
Nam-Hyun Cho, Hong-Joon Kwon, Young-Chan Suh and Jangrak Kim    
Airports strive to prevent safety issues, such as foreign object debris (FOD), by pavement management using the pavement condition index (PCI). The index is used in decision-making processes for overall pavement maintenance and repair, such as the preven... ver más
Revista: Applied Sciences

 
A. J. Prieto, F. Guiñez, M. Ortiz and M. González    
Concerning one of the most important tasks of road structure management is the development of methods to predict their own functional or physical service life, which allows for objectively evaluating the state of road structures that are being considered... ver más
Revista: Infrastructures

 
Shahin Eskandarsefat, Loretta Venturini, Augusto Ciarlitti, Enea Sogno and Isabella Ottonelli    
Ever-increasing traffic loads, in addition to hot climates, have always been a challenge for both road pavement authorities and engineers. Technically, asphalt binder and concrete modifiers that generally increase the viscosity and provide higher resista... ver más
Revista: Infrastructures

 
Nan Yang, Yongshang Li and Ronggui Ma    
Thanks to the development of deep learning, the use of data-driven methods to detect pavement distresses has become an active research field. This research makes four contributions to address the problem of efficiently detecting cracks and sealed cracks ... ver más
Revista: Applied Sciences