Framework of Data Acquisition and Integration for the Detection of Pavement Distress via Multiple Vehicles

Street defects, such as potholes and sunken manholes, in general develop quickly compared to other pavement distresses, such as cracking and rutting. Those street defects can result in vehicle damage. This paper proposes an automated and innovative method to obtain up-to-date information about those street defects with the use of a mobile data collection kit mounted on vehicles. In each mobile data collection kit, a triaxial accelerometer and global positioning system sensor collect data for the detection of street defects. A local algorithm is embedded in the mobile data collection kit to increase the efficiency of a local data logging process and to perform a preliminary detection of street defects. At a back-end server, a more precise street defect detection algorithm enhances the performance of the proposed monitoring system by integrating data collected from multiple sensor-equipped vehicles. The street defect detection algorithm at the back-end server relies on a supervised machine learning technique and a trajectory clustering algorithm. The framework of the data collection and integration is developed for the detection of isolated street defects and rough road conditions. The potential of detecting these conditions based on the dynamic responses of vehicles using machine learning techniques is investigated on real road conditions. The preliminary ratings for pavement distress are calculated by integrating the three classification results. Road networks that have isolated street defects and rough road surfaces are identified and visualized on an online map. The proposed system is of practical importance since it provides continuous information about road conditions, which can be valuable for pavement management systems and public safety.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01634235
  • Record Type: Publication
  • Files: TRIS, ASCE
  • Created Date: May 1 2017 9:45AM