A New Watershed Algorithm for Pothole Image Segmentation

Abstract

The road casualties caused by poor road conditions, especially potholed roads, amount to a high percentage of 13% per year in Asia. In order for the government to carry out repair works, they must know the surface area of the potholed road, the depth of the potholes, and the position of the potholes. In this paper, with the purpose of determining the surface area of the potholed road, segmentation was carried out first. The segmentation method used here is a new watershed algorithm. This algorithm includes six processes: smoothing, calculating the gradient value, automatic determination of minimum flooding value, combining the catchment basins, erasing the remaining watershed lines, and creating a watershed curve. The proposed algorithm is evaluated and compared with previously analysed watershed segmentation methods. This study shows that this algorithm is effective for reducing the effects of excessive segmentation. The proposed algorithm obtained a high accuracy of 95.34%, which is higher than that of the existing watershed segmentation methods.

Keywords

• potholes road image
• segmentation
• watershed
• a new watershed algorithm