Author ORCID Identifier
Date of Graduation
Statler College of Engineering and Mineral Resources
Civil and Environmental Engineering
Tack coat is a thin asphalt applied between the existing surface and asphalt overlay during road rehabilitation. The uniformity of tack coat coverage plays a vital role in providing adhesive bonding between the two layers in the pavement structures. To ensure tack coat uniformity, the current practice primarily relies on manual inspection during construction by field experts. This process is time-consuming and tedious, and the results can be subjective and error-prone. Drones have emerged as a non-destructive sensing technology in the construction industry for many inspection practices. Unlike other non-destructive inspection technologies, drones offer benefits ranging from accelerating data collection to accessing hard-to-read surface locations.
The research investigated the potential of drone applications to accelerate tack coat image acquisition with the combination of computer vision-based techniques to automatically analyze and interpret the drone-collected images. As a result, a novel method for automatic uniformity inspection of tack coat coverage using images collected by drones is presented. In this method, the color thresholding technique is first adopted to extract the coarse region of the tack coat. Based on this, the boundaries of the tack coat are then detected to refine the tack coat region and mask the objects that do not belong to the tack coat. After that, the region of interest is processed to extract the texture features using gray-level co-occurrence (GLCM). Finally, the texture feature information is leveraged to grade the tack coat uniformity level with the use of LightGBM. Experiments were conducted to examine the performance of the proposed method. The resulting accuracy signifies the potential of this method in developing high-efficient and cost-effective solutions to enhance the current tack coat inspection practice.
da Silva, Aida, "A Computer Vision-based Method for Tack Coat Coverage Inspection Using Drone-Collected Images" (2023). Graduate Theses, Dissertations, and Problem Reports. 11752.
Available for download on Friday, April 26, 2024