Crack sealing is a very important maintenance technique that is used to prevent water and debris from entering the pavement and to extend pavement life by minimizing crack growth. Manual crack sealing is an expensive procedure that is labor intensive and hazardous. Automating the crack sealing will improve work efficiency and decreases labor cost.
There are four main components of a crack sealing machine: image acquisition, crack map detection, path planning, and sealant application. Automation of crack map detection for the crack sealing machine has been a challenge. In contrast to the requirements for pavement-distress-survey systems, automated crack-sealing machinery must accurately locate individual crack segments so that they can be processed effectively. Secondly, many crack map detection algorithms are not suited for the automatic crack sealers because these algorithms give crack map outputs that are not continuous paths. This makes it harder to use the crack map directly for the optimal path planning process.
The user can detect continuous cracks that extend over several miles by just providing the starting point on a crack as input to the algorithm. The algorithm can also detect transverse cracks by giving a single point on the crack. The continuous crack map generated can be utilized very efficiently to generate the optimal path for the crack sealer. Extensive qualitative and quantitative evaluation on real pavement images was done to show the usefulness of the algorithm. The algorithm is also computationally fast and efficient. We hope that this work will be useful for the efficiency and automation of the crack sealing process.