Implementation of Automated Network-Level Crack Detection Processes in Maryland

Abstract

The Maryland State Highway Administration (MDSHA) has collected cracking data on its roadways for use in its pavement management system since 1984. Through much of this history the pavement cracking survey was performed yearly by teams of inspectors riding in vans. With the reengineering of the administration over the years, this process began to present serious resource and logistical problems. During the past 3 years, the MDSHA pavement management group has developed and implemented a state-of-the-art automated network-level crack detection process that is showing promising results. This process is based upon the use of the automated road analyzer (ARAN) data collection vehicle, Wisecrax crack detection software, and an intensive quality-control (QC) and quality-assurance (QA) procedure. The data collection and data processing tasks are all performed in house with MDSHA resources. An overview of the processes developed and implemented by MDSHA to conduct these surveys is provided. Also discussed are challenges and lessons learned during the implementation process. Presentation of this information will allow others to gain insight into the strengths and weaknesses of adopting such a system and promote information sharing among pavement data collection organizations. Overall, it is concluded that automated network-level crack detection is a workable and efficient tool. However, a strict QC-QA regime must be instituted in order to achieve consistent and repeatable results.