Redirigiendo al acceso original de articulo en 19 segundos...
Inicio  /  Water  /  Vol: 15 Par: 19 (2023)  /  Artículo
ARTÍCULO
TITULO

Ground Penetrating Radar Image Recognition for Earth Dam Disease Based on You Only Look Once v5s Algorithm

Binghan Xue    
Jianglin Gao    
Songtao Hu    
Yan Li    
Jianguo Chen and Rui Pang    

Resumen

The Ground Penetrating Radar (GPR) method is a commonly used method for earth dam disease detection. However, the major challenge is that the obtained GPR image data of earth dam disease mainly relies on human judgment, especially in long-distance earth dam disease detection, which may lead to misjudgments and omissions. The You Only Look Once v5s (YOLOv5s) algorithm is innovatively employed for GPR image recognition to address the current challenge. The YOLOv5s neural network model has advantages over the traditional convolutional neural network in terms of object detection speed and accuracy. In this study, an earth dam disease detection model was established based on YOLOv5s. Raw images from actual earth dam disease detection and GPR forward simulation images were used as the initial dataset. Data augmentation techniques were applied to expand the original dataset. The LabelImg annotation tool was employed to classify and label earth dam disease, thereby creating an object detection dataset that includes earth dam disease features. The model was trained within this dataset. The results indicate that the total loss function of the model trained on the custom dataset initially decreases and then stabilizes, showing no signs of overfitting and demonstrating good generalizability. The earth dam disease detection model based on YOLOv5s achieved average precision rates of 96.0%, 95.5%, and 93.9% for voids, seepage, and loosening disease, respectively. It can be concluded that the earth dam disease detection model based on YOLOv5s may be an effective tool for intelligent GPR image recognition in identifying earth dam disease.

 Artículos similares

       
 
Andres Gallego and Francisco Roman    
Complex natural resonances (CNRs) extraction methods such as matrix pencil method (MPM), Cauchy, vector-fitting Cauchy method (VCM), or Prony?s method decompose a signal in terms of frequency components and damping factors based on Baum?s singularity exp... ver más
Revista: Algorithms

 
Luca Bertolini, Fabrizio D?Amico, Antonio Napolitano, Luca Bianchini Ciampoli, Valerio Gagliardi and Jhon Romer Diezmos Manalo    
Monitoring of critical civil engineering infrastructures has become a priority for public owners and administrative authorities. Several laws and regulations have been issued on this topic, emphasizing the crucial role of Building Information Modeling (B... ver más
Revista: Infrastructures

 
Chuanxi Luo, Duanyi Wang, Jian Li and Jun He    
This study focuses on unknown crystal precipitates from an asphalt mixture used in bridge deck pavement layers. X-ray fluorescence spectroscopy was used to analyze the composition and source of crystals in the asphalt mixture used in bridge deck pavement... ver más
Revista: Buildings

 
Joseph P. Honings, Carol M. Wicks and Steven T. Brantley    
Increasing demand for water for agricultural use within the Dougherty Plain of the southeastern United States has depleted surface water bodies. In karstic landscapes, such as the Dougherty Plain in southwest Georgia where the linkages between surface an... ver más
Revista: Hydrology

 
Junli Zhai, Qiang Wang, Haozheng Wang, Xiongyao Xie, Mingyi Zhou, Dongyang Yuan and Weikang Zhang    
In order to overcome the difficulty in rapid detection for expressway tunnels, the coherence calculation of dual-frequency radar signal in the time domain is proposed to suppress the interference. A dual-frequency (400 MHz and 900 MHz) GPR and a manipula... ver más
Revista: Applied Sciences