Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Computer Vision-Based Severity Classification of Asphalt Pavement Raveling Using Advanced Gradient Boosting Machines and Lightweight Texture Descriptors
https://orcid.org/http://orcid.org/0000-0001-9450-4637
Automatic detection of raveled areas and categorization of their severity are crucial for assessing maintenance requirements and guaranteeing driving safety. This paper proposes and verifies a computer vision-based method for achieving these tasks. Advanced gradient boosting machines including adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), and extreme gradient boosting machine (XGBoost) are employed as pattern classifiers. To address the need to inspect large areas of pavement surfaces, this study also focuses on lightweight texture descriptors to enhance the productivity of the classification process. The employed texture descriptors are local binary pattern (LBP), center-symmetric local binary pattern (CSLBP), completed local binary pattern (CLBP), and local ternary pattern (LTP). These texture computation methods are selected due to their high performance for texture analysis, ease of implementation, and low computational cost. Experimental results supported by statistical tests point out that XGBoost coupled with CLBP achieves the most desired classification performance with Cohen’s kappa coefficients > 0.94. Therefore, the proposed approach can be a promising tool to assist pavement management authorities in the task of surveying road surface conditions.
Computer Vision-Based Severity Classification of Asphalt Pavement Raveling Using Advanced Gradient Boosting Machines and Lightweight Texture Descriptors
https://orcid.org/http://orcid.org/0000-0001-9450-4637
Automatic detection of raveled areas and categorization of their severity are crucial for assessing maintenance requirements and guaranteeing driving safety. This paper proposes and verifies a computer vision-based method for achieving these tasks. Advanced gradient boosting machines including adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), and extreme gradient boosting machine (XGBoost) are employed as pattern classifiers. To address the need to inspect large areas of pavement surfaces, this study also focuses on lightweight texture descriptors to enhance the productivity of the classification process. The employed texture descriptors are local binary pattern (LBP), center-symmetric local binary pattern (CSLBP), completed local binary pattern (CLBP), and local ternary pattern (LTP). These texture computation methods are selected due to their high performance for texture analysis, ease of implementation, and low computational cost. Experimental results supported by statistical tests point out that XGBoost coupled with CLBP achieves the most desired classification performance with Cohen’s kappa coefficients > 0.94. Therefore, the proposed approach can be a promising tool to assist pavement management authorities in the task of surveying road surface conditions.
Computer Vision-Based Severity Classification of Asphalt Pavement Raveling Using Advanced Gradient Boosting Machines and Lightweight Texture Descriptors
https://orcid.org/http://orcid.org/0000-0001-9450-4637
Automatic detection of raveled areas and categorization of their severity are crucial for assessing maintenance requirements and guaranteeing driving safety. This paper proposes and verifies a computer vision-based method for achieving these tasks. Advanced gradient boosting machines including adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), and extreme gradient boosting machine (XGBoost) are employed as pattern classifiers. To address the need to inspect large areas of pavement surfaces, this study also focuses on lightweight texture descriptors to enhance the productivity of the classification process. The employed texture descriptors are local binary pattern (LBP), center-symmetric local binary pattern (CSLBP), completed local binary pattern (CLBP), and local ternary pattern (LTP). These texture computation methods are selected due to their high performance for texture analysis, ease of implementation, and low computational cost. Experimental results supported by statistical tests point out that XGBoost coupled with CLBP achieves the most desired classification performance with Cohen’s kappa coefficients > 0.94. Therefore, the proposed approach can be a promising tool to assist pavement management authorities in the task of surveying road surface conditions.
Computer Vision-Based Severity Classification of Asphalt Pavement Raveling Using Advanced Gradient Boosting Machines and Lightweight Texture Descriptors
Iran J Sci Technol Trans Civ Eng
Nhat-Duc, Hoang (Autor:in) / Van-Duc, Tran (Autor:in)
01.12.2023
15 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Engineering Index Backfile | 1959