Using support vector machines to predict the probability of pavement failure

Schlotjes, Megan Rose; Burrow, Michael; Evdorides, Harry; Henning, Theunis F. P.

doi:10.1680/tran.12.00084

Cited by 15 publications

(9 citation statements)

References 17 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An SVM is a classification system derived from statistical learning theory. It separates the classes with a decision surface that maximizes the margin between the classes [27]. The surface is often called the optimal hyperplane, and the data points closest to the hyperplane are called support vectors.…”

Section: Support Vector Machinementioning

confidence: 99%

“…However, the automatic detection of pavement distresses based on an image processing method would become more complex and challenging for images with high variations of lighting and road surface texture [25], [26]. With the development of artificial intelligence in recent years, some machine learning algorithms were introduced into the automatic pavement defects detection field, such as a support vector machine (SVM) [27], [28], an artificial neural network (ANN) [29], [30], and a random forest (RF) [31]. For example, Xu segmented the pavement images into a number of square tiles and then extracted four customized features of tiles to train the BP neural networks to identify the crack tiles [30].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

Pan

Zhang

Cervone

et al. 2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

149

View full text Add to dashboard Cite

Asphalt roads are the basic component of a land transportation system, and the quality of asphalt roads will decrease during the use stage because of the aging and deterioration of the road surface. In the end, some road pavement distresses may appear on the road surface, such as the most common potholes and cracks. In order to improve the efficiency of pavement inspection, currently some new forms of remote sensing data without destructive effect on the pavement are widely used to detect the pavement distresses, such as digital images, light detection and ranging, and radar. Multispectral imagery presenting spatial and spectral features of objects has been widely used in remote sensing application. In our study, the multispectral pavement images acquired by unmanned aerial vehicle (UAV) were used to distinguish between the normal pavement and pavement damages (e.g., cracks and potholes) using machine learning algorithms, such as support vector machine, artificial neural network, and random forest. Comparison of the performance between different data types and models was conducted and is discussed in this study, and indicates that a UAV remote sensing system offers a new tool for monitoring asphalt road pavement condition, which can be used as decision support for road maintenance practice. Index Terms-Artificial neural network (ANN), asphalt roads, multispectral imagery, pavement distress, random forest (RF), support vector machine (SVM), unmanned aerial vehicle (UAV). I. INTRODUCTIONR OADS, as one of the most important infrastructures, play a crucial role in supporting the development of an economy and human society. Therefore, it is imperative to maintain roads in a good condition. The quality of road pavement directly Manuscript

show abstract

Section: Support Vector Machinementioning

confidence: 99%

mentioning

confidence: 99%

Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

Pan

Zhang

Cervone

et al. 2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

149

View full text Add to dashboard Cite

show abstract

“…With the development of artificial intelligence methods, new automated techniques for pavement distress detection have been designed. Support vector machines are commonly used for classification problems in computer vision based applications [63][64][65]. However, with the advent of deep learning technology, Convolutional Neural Networks (ConvNets) have started to dominate the field of object detection and recognition in vision based areas [13,51,55,66], as those methods perform feature extraction without requiring a separate feature extraction system.…”

Section: Source Input Data and Data Collectionmentioning

confidence: 99%

Pavement Distress Detection with Deep Learning Using the Orthoframes Acquired by a Mobile Mapping System

et al. 2019

View full text Add to dashboard Cite

The subject matter of this research article is automatic detection of pavement distress on highway roads using computer vision algorithms. Specifically, deep learning convolutional neural network models are employed towards the implementation of the detector. Source data for training the detector come in the form of orthoframes acquired by a mobile mapping system. Compared to our previous work, the orthoframes are generally of better quality, but more importantly, in this work, we introduce a manual preprocessing step: sets of orthoframes are carefully selected for training and manually digitized to ensure adequate performance of the detector. Pretrained convolutional neural networks are then fine-tuned for the problem of pavement distress detection. Corresponding experimental results are provided and analyzed and indicate a successful implementation of the detector.

show abstract

“…A support vector machine (SVM) is a technique for machine learning; it has been used previously for, among other applications, predicting the probability of pavement failure (Schlotjes et al, 2015). Singh et al (2018) use the same technique for predicting road traffic accidents.…”

mentioning

confidence: 99%

Editorial

Polack¹

2018

Proceedings of the Institution of Civil Engineers - Transport

View full text Add to dashboard Cite

Modellingthe construction of a virtual representation of a physical situation or processis now an essential component of most projects. Models allow engineers to forecast likely outcomes based on past experience, and then design appropriate mitigating measures. Just as importantly, models allow engineers to experiment in a 'risk-free' environment. Of course, in order for engineers to have confidence in a model it is essential that the output is validated to ensure that it correlates with the observed physical outcomes. Modelling is the common theme running through all the papers in this issue of Transport. Applications range from a high-speed rail network in Spain, by way of highways in Brazil to internal air routes in Iran.

show abstract

Using support vector machines to predict the probability of pavement failure

Abstract: Using support vector machines to predict the probability of pavement failure Schlotjes, Burrow, Evdorides and Henning

Cited by 15 publications

References 17 publications

Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

Detection of Asphalt Pavement Potholes and Cracks Based on the Unmanned Aerial Vehicle Multispectral Imagery

Pavement Distress Detection with Deep Learning Using the Orthoframes Acquired by a Mobile Mapping System

Editorial

Contact Info

Product

Resources

About