An Artificial Intelligence Method for Asphalt Pavement Pothole Detection Using Least Squares Support Vector Machine and Neural Network with Steerable Filter‐Based Feature Extraction

Hoang, Nhat‐Duc

doi:10.1155/2018/7419058

Cited by 111 publications

(53 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(1) Connected domain feature: the number of connected domains of potholes, transverse cracks, and longitudinal cracks is 1 while the largest connected domain is extracted, and the number of connected domains of complex cracks is more than 1. erefore, the number of connected domains can be used to distinguish the types of pavement defects. (2) Projection feature [14]: projection is highly useful for characterizing the type of defects in cement concrete pavement because different types of defects tend to have distinctive projection properties. Project a binary image to the X and Y axes and count the number of pixels in the horizontal and vertical directions.…”

Section: Feature Selection and Calculationmentioning

confidence: 99%

“…After problems (14) and (15) are solved, find the optimal solution α * i ; the optimal ω and b satisfy…”

Section: Support Vector Machinementioning

confidence: 99%

“…Current pothole detection methods can be divided into two groups: manual and automatic. e traditional manual approaches can help detect and evaluate potholes, but it is time-consuming, labor-intensive, and expensive [13,14]. Moreover, while well-defined criteria for assessment exist, subjectivity and experience of the raters affect the ratings [15].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Gao

Wang

Zhu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Potholes are the most common form of distress on cement concrete pavements, which can compromise pavement safety and ridability. Thus, timely and accurate pothole detection is an important task in developing proper maintenance strategies and ensuring driving safety. This paper proposes a method of integrating the processing of grayscale and texture features. This method mainly combines industrial camera to realize rapid and accurate detection of pothole. Image processing techniques including texture filters, image grayscale, morphology, and extraction of the maximum connected domain are used synergistically to extract useful features from digital images. A machine learning model based on the library for support vector machine (LIBSVM) is constructed to distinguish potholes from longitudinal cracks, transverse cracks, and complex cracks. The method is validated using data collected from agricultural and pastoral areas of Inner Mongolia, China. The comprehensive experiments for recognition of potholes show that the recall, precision, and F1-Score achieved are 100%, 97.4%, and 98.7%, respectively. In addition, the overlap rate between the extracted pothole region and the original image is estimated. Images with an overlap rate greater than 90% accounted for 76.8% of the total image, and images with an overlap rate greater than 80% accounted for 94% of the total image. A comparison discloses that the proposed approach is superior to the existing method not only from the perspective of the accuracy of pothole detection but also from the perspective of the segmentation effect and processing efficiency.

show abstract

Section: Feature Selection and Calculationmentioning

confidence: 99%

“…After problems (14) and (15) are solved, find the optimal solution α * i ; the optimal ω and b satisfy…”

Section: Support Vector Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Gao

Wang

Zhu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…To collect pavement distress data, two main approaches are usually used by road agencies: manual and automated distress data collections [24]. e automated approach is costly because not only advanced equipment is required, but also subsequent photographs need to be processed.…”

Section: Distress Types Surveymentioning

confidence: 99%

Research on Relationships among Different Distress Types of Asphalt Pavements with Semi‐Rigid Bases in China Using Association Rule Mining: A Statistical Point of View

Jing

Liu

Yang

et al. 2019

Advances in Civil Engineering

View full text Add to dashboard Cite

Distress types are significant for asphalt pavement maintenance decision, and relationships among them can greatly influence the decision outcomes. In this study, to analyze the relationships among different distress types from a statistical point of view, 282 asphalt pavements with semirigid base structures in 23 regions of China were surveyed to identify 12 distress types, which were subsequently investigated by association rule mining. Results show that the distress types can be categorized into independent distress types (IDDTs), dependent distress types (DDTs), and rutting secondary distress types (RSDTs) based on the relationships. The relationships among IDDTs are the strongest, and those between IDDTs and DDTs, between rutting and RSDTs, and among depression, pumping, and raveling are also strong, while the others are weak. The weak relationships should be ignored, while the strong ones should be considered to reduce cost and guarantee accuracy of maintenance decision. The IDDTs are the most important distress types, so preventing them from occurring or maintaining them immediately can greatly preserve good performance of asphalt pavements. To help analyze the relationships, a distress-type system was established and verified. In conclusion, this work provides new insights to understand distress types.

show abstract

“…As demonstrated in the previous works of Cubero-Fernandez et al [6] and Hoang and Nguyen [2], this image enhancement technique is particularly useful for differentiating the crack patterns and the background texture of asphalt pavement. In addition to crack detection, SF has been successfully employed in other tasks of the computer vision field such as object tracking, text classification, and distress recognition [3,[24][25][26].…”

Section: Steerable Filter (Sf)mentioning

confidence: 99%

Automatic Recognition of Asphalt Pavement Cracks Based on Image Processing and Machine Learning Approaches: A Comparative Study on Classifier Performance

Hoang

Nguyen

2018

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Periodic surveys of asphalt pavement condition are very crucial in road maintenance. This work carries out a comparative study on the performance of machine learning approaches used for automatic pavement crack recognition. Six machine learning approaches, Naïve Bayesian Classifier (NBC), Classification Tree (CT), Backpropagation Artificial Neural Network (BPANN), Radial Basis Function Neural Network (RBFNN), Support Vector Machine (SVM), and Least Squares Support Vector Machine (LSSVM), have been employed. Additionally, Median Filter (MF), Steerable Filter (SF), and Projective Integral (PI) have been used to extract useful features from pavement images. In the feature extraction phase, performance comparison shows that the input pattern including the diagonal PIs enhances the classification performance significantly by creating more informative features. A simple moving average method is also employed to reduce the size of the feature set with positive effects on the model classification performance. Experimental results point out that LSSVM has achieved the highest classification accuracy rate. Therefore, this machine learning algorithm used with the feature extraction process proposed in this study can be a very promising tool to assist transportation agencies in the task of pavement condition survey.

show abstract

An Artificial Intelligence Method for Asphalt Pavement Pothole Detection Using Least Squares Support Vector Machine and Neural Network with Steerable Filter‐Based Feature Extraction

Cited by 111 publications

References 37 publications

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Research on Relationships among Different Distress Types of Asphalt Pavements with Semi‐Rigid Bases in China Using Association Rule Mining: A Statistical Point of View

Automatic Recognition of Asphalt Pavement Cracks Based on Image Processing and Machine Learning Approaches: A Comparative Study on Classifier Performance

Contact Info

Product

Resources

About