Asphalt pavement paving segregation detection method using more efficiency and quality texture features extract algorithm

• Published in: Construction & building materials Vol. 277; p. 122302
• Main Authors: Zhao, Xun, Xue, Lige, Xu, Feiyun
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 29.03.2021
• Subjects: GLCM; Paving segregation detection; SVM; Texture feature extraction; Uniform pattern LBP; Texture feature extraction; SVM; GLCM; Uniform pattern LBP; Paving segregation detection
• ISSN: 0950-0618; 1879-0526
• DOI: 10.1016/j.conbuildmat.2021.122302

•Asphalt paving segregation detection using image texture features.•Texture feature extraction algorithm combining uniform pattern LBP and GLCM.•Asphalt paving segregation detection based on uniform pattern LBP-GLCM.•The support vector machine classifier is used to detection whether paving segregation occurs. The segregation of asphalt pavement is the main reason for the decrease of safety, comfort and actual service life of the road, and the paving segregation is the main inducement for asphalt pavements segregation. Thus, a kind of effective paving segregation detection method can reduce the occurrence of asphalt pavement segregation. The traditional asphalt segregation detection methods are mainly divided into contact detection and non-contact detection. The contact detection method can only detect the segregation of pavement after paving or in use, and the non-contact detection method is also generally limited by the noise and expensive equipment. In recent years, the rapid development of image processing technology has provided a new research direction for asphalt paving segregation detection, but the accuracy and efficiency of the existing image-based asphalt paving segregation detection methods are insufficient. In order to solve these problems, this paper proposes an asphalt paving segregation detection method based on image texture features. Firstly, based on the traditional algorithms LBP (Local Binary Pattern) and GLCM (Gray-level Co-occurrence Matrix), a new texture feature extraction algorithm uniform pattern LBP-GLCM is proposed. Secondly, a detection method based on uniform pattern LBP-GLCM in combination with SVM (Support Vector Machine) is proposed. Then, the detection method proposed is validated using Kylbery texture dataset, the result show that this detection methods has great accuracy and efficiency in the classification of targets with similar texture features, it also means the texture feature extract method based on uniform pattern LBP-GLCM can combine the advantages of LBP and GLCM to achieve improvement of feature extraction's performance and efficiency. Finally, the detection method is applied to the diagnosis of asphalt paving segregation, and the accuracy of diagnosis achieves 94%. Compared with the existing algorithms, detection method based on uniform pattern LBP-GLCM has higher diagnostic accuracy and efficiency. Specifically, detection method with uniform pattern LBP-GLCM can improve accuracy in comparison with single asphalt pavement paving segregation detection method, and it can improve efficiency in comparison with existing hybrid asphalt pavement paving segregation detection method. The results of this study can potentially be used for real-time detection of asphalt paving segregation.