Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using eXtreme Gradient Boost

The raveling of asphalt pavement is the primary cause of decreasing road safety, comfort, and service life. Because of the asphalt's complex texture, automatic raveling detection from image samples is a challenging operation. In this study, a computer vision technique, based on image texture features, for automatic detection of asphalt pavement raveling is proposed and verified. Two scenarios are taken into account for feature extraction. First, texture features from images are extracted using the traditional GLCM (Gray-Level Co-occurrence Matrix) algorithm. Second, the images are subjected to LBP (Local Binary Pattern) and then GLCM is employed to extract texture features. Utilizing the eXtreme Gradient Boost (XGBoost) technique, two models are built using the mentioned feature extraction scenarios and then compared. The results indicate that compared to the first scenarios prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %81), the second feature extraction scenario can offer higher prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %97). In order to demonstrate the model’s generalizability, a separate dataset is tested. Due to the acceptable performance values for this dataset (with more than %97 in terms of Accuracy, Precision, Recall, and F1-Score), the suggested model can be beneficial for transportation agencies to enhance the efficiency of road inspection activities.

• Record URL:
  • https://doi.org/10.1016/j.conbuildmat.2023.132731
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0950061823024479
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/09500618
• Supplemental Notes:
  • © 2023 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Daneshvari, Mohammad Hassan
  • Nourmohammadi, Ebrahim
  • Ameri, Mahmoud
  • Mojaradi, Barat
  • 0000-0002-5894-5969
• Publication Date: 2023-10-19

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 132731
• Serial:
  • Construction and Building Materials
  • Volume: 401
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0950-0618
  • Serial URL: http://www.sciencedirect.com/science/journal/09500618?sdc=1

Subject/Index Terms

• TRT Terms: Asphalt pavements; Computer vision; Stripping (Pavements); Visual texture recognition
• Identifier Terms: eXtreme Gradient Boosting (XGB) algorithm
• Subject Areas: Data and Information Technology; Highways; Maintenance and Preservation; Pavements;

Filing Info

• Accession Number: 01893592
• Record Type: Publication
• Files: TRIS
• Created Date: Sep 19 2023 9:32AM